Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+CAFM-JiT-H-16-256/demo.png filter=lfs diff=lfs merge=lfs -text
+CAFM-SiT-XL-2-256/demo.png filter=lfs diff=lfs merge=lfs -text
+CAFM-Z-Image-T2I/demo.png filter=lfs diff=lfs merge=lfs -text
+CAFM-Z-Image-T2I/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

CAFM-JiT-H-16-256/generator/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CAFMJiTGenerator2DModel",
+  "_diffusers_version": "0.36.0",
+  "sample_size": 256,
+  "patch_size": 16,
+  "hidden_size": 1280,
+  "num_layers": 32,
+  "num_attention_heads": 16,
+  "bottleneck_dim": 256,
+  "in_context_len": 32,
+  "in_context_start": 10,
+  "attention_dropout": 0.0,
+  "dropout": 0.2,
+  "num_classes": 1000,
+  "in_channels": 3,
+  "mlp_ratio": 4.0,
+  "norm_eps": 1e-06
+}

CAFM-JiT-H-16-256/generator/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc3e1ba8899d8a9fbfdcb0606cd1e41c68d5881994611cad7959209aadac592
+size 3811413896

CAFM-JiT-H-16-256/generator/modeling_cafm_jit.py

@@ -0,0 +1,573 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import math
+
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+from diffusers.models.normalization import RMSNorm
+from diffusers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+
+def broadcat(tensors, dim=-1):
+    num_tensors = len(tensors)
+    shape_lens = {len(t.shape) for t in tensors}
+    if len(shape_lens) != 1:
+        raise ValueError("tensors must all have the same number of dimensions")
+    shape_len = list(shape_lens)[0]
+    dim = (dim + shape_len) if dim < 0 else dim
+    dims = list(zip(*(list(t.shape) for t in tensors)))
+    expandable_dims = [(i, val) for i, val in enumerate(dims) if i != dim]
+
+    if not all(len(set(t[1])) <= 2 for t in expandable_dims):
+        raise ValueError("invalid dimensions for broadcastable concatenation")
+
+    max_dims = [(t[0], max(t[1])) for t in expandable_dims]
+    expanded_dims = [(t[0], (t[1],) * num_tensors) for t in max_dims]
+    expanded_dims.insert(dim, (dim, dims[dim]))
+    expandable_shapes = list(zip(*(t[1] for t in expanded_dims)))
+    tensors = [t[0].expand(*t[1]) for t in zip(tensors, expandable_shapes)]
+    return torch.cat(tensors, dim=dim)
+
+
+def rotate_half(x):
+    x = x.view(*x.shape[:-1], x.shape[-1] // 2, 2)
+    x1, x2 = x.unbind(dim=-1)
+    x = torch.stack((-x2, x1), dim=-1)
+    return x.view(*x.shape[:-2], -1)
+
+
+class JiTRotaryEmbedding(nn.Module):
+    def __init__(
+        self,
+        dim,
+        pt_seq_len=16,
+        ft_seq_len=None,
+        custom_freqs=None,
+        theta=10000,
+        num_cls_token=0,
+    ):
+        super().__init__()
+        self.dim = dim
+        self.pt_seq_len = pt_seq_len
+        self.theta = theta
+        self.num_cls_token = num_cls_token
+        self.custom_freqs = custom_freqs
+        if ft_seq_len is None:
+            ft_seq_len = pt_seq_len
+        self._cached_hw = None
+        cos, sin = self._build_freqs(ft_seq_len, ft_seq_len, device=torch.device("cpu"))
+        self.register_buffer("freqs_cos", cos, persistent=False)
+        self.register_buffer("freqs_sin", sin, persistent=False)
+        self._cached_hw = (ft_seq_len, ft_seq_len)
+
+    def _build_freqs(self, height, width, device):
+        if self.custom_freqs is not None:
+            freqs = self.custom_freqs.to(device=device, dtype=torch.float32)
+        else:
+            freqs = 1.0 / (
+                self.theta ** (torch.arange(0, self.dim, 2, device=device, dtype=torch.float32)[: (self.dim // 2)] / self.dim)
+            )
+
+        t_h = torch.arange(height, device=device, dtype=torch.float32) / height * self.pt_seq_len
+        t_w = torch.arange(width, device=device, dtype=torch.float32) / width * self.pt_seq_len
+        freqs_h = torch.einsum("..., f -> ... f", t_h, freqs).repeat_interleave(2, dim=-1)
+        freqs_w = torch.einsum("..., f -> ... f", t_w, freqs).repeat_interleave(2, dim=-1)
+        freqs_2d = broadcat((freqs_h[:, None, :], freqs_w[None, :, :]), dim=-1)
+        freqs_flat = freqs_2d.view(-1, freqs_2d.shape[-1])
+        cos_img = freqs_flat.cos()
+        sin_img = freqs_flat.sin()
+        if self.num_cls_token > 0:
+            _, dim_freq = cos_img.shape
+            cos_pad = torch.ones(self.num_cls_token, dim_freq, dtype=cos_img.dtype, device=device)
+            sin_pad = torch.zeros(self.num_cls_token, dim_freq, dtype=sin_img.dtype, device=device)
+            cos_img = torch.cat([cos_pad, cos_img], dim=0)
+            sin_img = torch.cat([sin_pad, sin_img], dim=0)
+        return cos_img, sin_img
+
+    def forward(self, t, height=None, width=None):
+        # Applied on (batch, seq_len, heads, head_dim) tensors from attention.
+        seq_len = t.shape[1]
+        if height is None or width is None:
+            image_tokens = seq_len - self.num_cls_token
+            size = int(image_tokens**0.5)
+            if size * size != image_tokens:
+                raise ValueError(
+                    f"Cannot infer square token grid from sequence length {seq_len} with {self.num_cls_token} class tokens."
+                )
+            height = size
+            width = size
+        if self._cached_hw != (height, width) or self.freqs_cos.device != t.device:
+            self.freqs_cos, self.freqs_sin = self._build_freqs(height, width, device=t.device)
+            self._cached_hw = (height, width)
+        freqs_cos = self.freqs_cos[:seq_len].to(t.dtype)
+        freqs_sin = self.freqs_sin[:seq_len].to(t.dtype)
+
+        return t * freqs_cos[:, None, :] + rotate_half(t) * freqs_sin[:, None, :]
+
+
+def modulate(x, shift, scale):
+    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)
+
+
+class JiTPatchEmbed(nn.Module):
+    """Image to Patch Embedding with Bottleneck"""
+
+    def __init__(self, img_size=224, patch_size=16, in_chans=3, pca_dim=768, embed_dim=768, bias=True):
+        super().__init__()
+        img_size = (img_size, img_size)
+        patch_size = (patch_size, patch_size)
+        self.img_size = img_size
+        self.patch_size = patch_size
+        self.num_patches = (img_size[1] // patch_size[1]) * (img_size[0] // patch_size[0])
+
+        self.proj1 = nn.Conv2d(in_chans, pca_dim, kernel_size=patch_size, stride=patch_size, bias=False)
+        self.proj2 = nn.Conv2d(pca_dim, embed_dim, kernel_size=1, stride=1, bias=bias)
+
+    def forward(self, x):
+        x = self.proj2(self.proj1(x)).flatten(2).transpose(1, 2)
+        return x
+
+
+class JiTTimestepEmbedder(nn.Module):
+    """
+    Embeds scalar timesteps into vector representations.
+    """
+
+    def __init__(self, hidden_size, frequency_embedding_size=256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t, dim, max_period=10000):
+        """
+        Create sinusoidal timestep embeddings.
+        """
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half
+        ).to(device=t.device)
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t, dtype=None):
+        t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        if dtype is not None:
+            t_freq = t_freq.to(dtype=dtype)
+        t_emb = self.mlp(t_freq)
+        return t_emb
+
+
+class JiTLabelEmbedder(nn.Module):
+    """
+    Embeds class labels into vector representations.
+    """
+
+    def __init__(self, num_classes, hidden_size):
+        super().__init__()
+        self.embedding_table = nn.Embedding(num_classes + 1, hidden_size)
+        self.num_classes = num_classes
+
+    def forward(self, labels):
+        embeddings = self.embedding_table(labels)
+        return embeddings
+
+
+class JiTAttention(nn.Module):
+    def __init__(self, dim, num_heads=8, qkv_bias=True, qk_norm=True, attn_drop=0.0, proj_drop=0.0, eps=1e-6):
+        super().__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+
+        self.q_norm = RMSNorm(head_dim, eps=eps) if qk_norm else nn.Identity()
+        self.k_norm = RMSNorm(head_dim, eps=eps) if qk_norm else nn.Identity()
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = attn_drop
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+    def forward(self, x, rope=None, grid_height=None, grid_width=None):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]
+
+        q = self.q_norm(q)
+        k = self.k_norm(k)
+
+        if rope is not None:
+            q = q.transpose(1, 2)
+            k = k.transpose(1, 2)
+            q = rope(q, height=grid_height, width=grid_width)
+            k = rope(k, height=grid_height, width=grid_width)
+            q = q.transpose(1, 2)
+            k = k.transpose(1, 2)
+
+        dropout_p = self.attn_drop if self.training else 0.0
+        x = F.scaled_dot_product_attention(q, k, v, dropout_p=dropout_p)
+        x = x.transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+
+class JiTSwiGLUFFN(nn.Module):
+    def __init__(self, dim: int, hidden_dim: int, drop=0.0, bias=True) -> None:
+        super().__init__()
+        hidden_dim = int(hidden_dim * 2 / 3)
+        self.w12 = nn.Linear(dim, 2 * hidden_dim, bias=bias)
+        self.w3 = nn.Linear(hidden_dim, dim, bias=bias)
+        self.ffn_dropout = nn.Dropout(drop)
+
+    def forward(self, x):
+        x12 = self.w12(x)
+        x1, x2 = x12.chunk(2, dim=-1)
+        hidden = F.silu(x1) * x2
+        return self.w3(self.ffn_dropout(hidden))
+
+
+class JiTBlock(nn.Module):
+    def __init__(self, hidden_size, num_heads, mlp_ratio=4.0, attn_drop=0.0, proj_drop=0.0, eps=1e-6):
+        super().__init__()
+        self.norm1 = RMSNorm(hidden_size, eps=eps)
+        self.attn = JiTAttention(
+            hidden_size,
+            num_heads=num_heads,
+            qkv_bias=True,
+            qk_norm=True,
+            attn_drop=attn_drop,
+            proj_drop=proj_drop,
+            eps=eps,
+        )
+        self.norm2 = RMSNorm(hidden_size, eps=eps)
+        mlp_hidden_dim = int(hidden_size * mlp_ratio)
+        self.mlp = JiTSwiGLUFFN(hidden_size, mlp_hidden_dim, drop=proj_drop)
+
+        self.act = nn.SiLU()
+        self.adaLN_modulation = nn.Linear(hidden_size, 6 * hidden_size, bias=True)
+
+    def forward(self, x, c, feat_rope=None, grid_height=None, grid_width=None):
+        # Apply activation
+        c = self.act(c)
+
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=-1)
+
+        # Attention block
+        norm_x = self.norm1(x)
+        modulated_x = modulate(norm_x, shift_msa, scale_msa)
+        attn_out = self.attn(modulated_x, rope=feat_rope, grid_height=grid_height, grid_width=grid_width)
+        x = x + gate_msa.unsqueeze(1) * attn_out
+
+        # MLP block
+        norm_x = self.norm2(x)
+        modulated_x = modulate(norm_x, shift_mlp, scale_mlp)
+        mlp_out = self.mlp(modulated_x)
+        x = x + gate_mlp.unsqueeze(1) * mlp_out
+
+        return x
+
+
+def get_2d_sincos_pos_embed(embed_dim, grid_size, cls_token=False, extra_tokens=0):
+    grid_h = np.arange(grid_size, dtype=np.float32)
+    grid_w = np.arange(grid_size, dtype=np.float32)
+    grid = np.meshgrid(grid_w, grid_h)
+    grid = np.stack(grid, axis=0)
+    grid = grid.reshape([2, 1, grid_size, grid_size])
+    pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
+    if cls_token and extra_tokens > 0:
+        pos_embed = np.concatenate([np.zeros([extra_tokens, embed_dim]), pos_embed], axis=0)
+    return pos_embed
+
+
+def get_2d_sincos_pos_embed_from_grid(embed_dim, grid):
+    if embed_dim % 2 != 0:
+        raise ValueError(f"embed_dim must be divisible by 2, but got {embed_dim}")
+
+    emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0])
+    emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1])
+    emb = np.concatenate([emb_h, emb_w], axis=1)
+    return emb
+
+
+def get_1d_sincos_pos_embed_from_grid(embed_dim, pos):
+    if embed_dim % 2 != 0:
+        raise ValueError(f"embed_dim must be divisible by 2, but got {embed_dim}")
+
+    omega = np.arange(embed_dim // 2, dtype=np.float64)
+    omega /= embed_dim / 2.0
+    omega = 1.0 / 10000**omega
+
+    pos = pos.reshape(-1)
+    out = np.einsum("m,d->md", pos, omega)
+
+    emb_sin = np.sin(out)
+    emb_cos = np.cos(out)
+
+    emb = np.concatenate([emb_sin, emb_cos], axis=1)
+    return emb
+
+
+class JiTTransformer2DModel(ModelMixin, ConfigMixin):
+    r"""
+    A 2D Transformer for pixel-space class-conditional generation with JiT
+    ([Back to Basics: Let Denoising Generative Models Denoise](https://arxiv.org/abs/2511.13720)).
+
+    Parameters:
+        sample_size (`int`, defaults to `256`):
+            Input image resolution (height and width).
+        patch_size (`int`, defaults to `16`):
+            Patch size for the bottleneck patch embedder.
+        in_channels (`int`, defaults to `3`):
+            Number of input image channels.
+        hidden_size (`int`, defaults to `768`):
+            Transformer hidden dimension.
+        num_layers (`int`, defaults to `12`):
+            Number of JiT transformer blocks.
+        num_attention_heads (`int`, defaults to `12`):
+            Number of attention heads per block.
+        mlp_ratio (`float`, defaults to `4.0`):
+            MLP hidden dimension multiplier.
+        attention_dropout (`float`, defaults to `0.0`):
+            Attention dropout in the middle quarter of blocks.
+        dropout (`float`, defaults to `0.0`):
+            Projection dropout in the middle quarter of blocks.
+        num_classes (`int`, defaults to `1000`):
+            Number of class labels (null label uses index `num_classes` for CFG).
+        bottleneck_dim (`int`, defaults to `128`):
+            PCA bottleneck dimension in the patch embedder.
+        in_context_len (`int`, defaults to `32`):
+            Number of in-context class tokens prepended mid-network.
+        in_context_start (`int`, defaults to `4`):
+            Block index at which in-context tokens are inserted.
+        norm_eps (`float`, defaults to `1e-6`):
+            Epsilon for RMSNorm layers.
+    """
+
+    _supports_gradient_checkpointing = True
+    _skip_layerwise_casting_patterns = ["pos_embed", "norm"]
+
+    @register_to_config
+    def __init__(
+        self,
+        sample_size: int = 256,
+        patch_size: int = 16,
+        in_channels: int = 3,
+        hidden_size: int = 768,
+        num_layers: int = 12,
+        num_attention_heads: int = 12,
+        mlp_ratio: float = 4.0,
+        attention_dropout: float = 0.0,
+        dropout: float = 0.0,
+        num_classes: int = 1000,
+        bottleneck_dim: int = 128,
+        in_context_len: int = 32,
+        in_context_start: int = 4,
+        norm_eps: float = 1e-6,
+    ):
+        super().__init__()
+        self.sample_size = sample_size
+        self.patch_size = patch_size
+        self.in_channels = in_channels
+        self.out_channels = in_channels
+        self.hidden_size = hidden_size
+        self.num_layers = num_layers
+        self.num_attention_heads = num_attention_heads
+        self.in_context_len = in_context_len
+        self.in_context_start = in_context_start
+        self.norm_eps = norm_eps
+        self.gradient_checkpointing = False
+
+        # Time and Class Embedding
+        self.t_embedder = JiTTimestepEmbedder(hidden_size)
+        self.y_embedder = JiTLabelEmbedder(num_classes, hidden_size)
+
+        # Patch Embedding
+        self.x_embedder = JiTPatchEmbed(
+            img_size=sample_size,
+            patch_size=patch_size,
+            in_chans=in_channels,
+            pca_dim=bottleneck_dim,
+            embed_dim=hidden_size,
+            bias=True,
+        )
+
+        # Positional Embedding (Fixed Sin-Cos)
+        num_patches = self.x_embedder.num_patches
+        pos_embed = get_2d_sincos_pos_embed(hidden_size, int(num_patches**0.5))
+        self.register_buffer("pos_embed", torch.from_numpy(pos_embed).float().unsqueeze(0), persistent=True)
+
+        # In-context Embedding
+        if self.in_context_len > 0:
+            self.in_context_posemb = nn.Parameter(torch.zeros(1, self.in_context_len, hidden_size))
+
+        # RoPE
+        half_head_dim = hidden_size // num_attention_heads // 2
+        hw_seq_len = sample_size // patch_size
+        self.feat_rope = JiTRotaryEmbedding(dim=half_head_dim, pt_seq_len=hw_seq_len, num_cls_token=0)
+        self.feat_rope_incontext = JiTRotaryEmbedding(
+            dim=half_head_dim, pt_seq_len=hw_seq_len, num_cls_token=self.in_context_len
+        )
+
+        # Blocks
+        self.blocks = nn.ModuleList(
+            [
+                JiTBlock(
+                    hidden_size,
+                    num_attention_heads,
+                    mlp_ratio=mlp_ratio,
+                    attn_drop=attention_dropout if (num_layers // 4 * 3 > i >= num_layers // 4) else 0.0,
+                    proj_drop=dropout if (num_layers // 4 * 3 > i >= num_layers // 4) else 0.0,
+                    eps=norm_eps,
+                )
+                for i in range(num_layers)
+            ]
+        )
+
+        # Final Layer
+        self.norm_final = RMSNorm(hidden_size, eps=norm_eps)
+        self.linear_final = nn.Linear(hidden_size, patch_size * patch_size * self.out_channels, bias=True)
+        self.act_final = nn.SiLU()
+        self.adaLN_modulation_final = nn.Linear(hidden_size, 2 * hidden_size, bias=True)
+
+    def _get_patch_grid(self, hidden_states):
+        height, width = hidden_states.shape[-2:]
+        if height % self.patch_size != 0 or width % self.patch_size != 0:
+            raise ValueError(
+                f"Input size {(height, width)} must be divisible by patch_size={self.patch_size}."
+            )
+        return height // self.patch_size, width // self.patch_size
+
+    def _interpolate_pos_encoding(self, tokens, grid_height, grid_width):
+        num_tokens = grid_height * grid_width
+        if self.pos_embed.shape[1] == num_tokens:
+            return self.pos_embed.to(device=tokens.device, dtype=tokens.dtype)
+        base_size = int(self.pos_embed.shape[1] ** 0.5)
+        pos_embed = self.pos_embed.reshape(1, base_size, base_size, self.hidden_size).permute(0, 3, 1, 2)
+        pos_embed = F.interpolate(pos_embed, size=(grid_height, grid_width), mode="bicubic", align_corners=False)
+        pos_embed = pos_embed.permute(0, 2, 3, 1).reshape(1, num_tokens, self.hidden_size)
+        return pos_embed.to(device=tokens.device, dtype=tokens.dtype)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.LongTensor,
+        class_labels: torch.LongTensor,
+        interpolate_pos_encoding: bool = True,
+        return_dict: bool = True,
+    ):
+
+        t_emb = self.t_embedder(timestep, dtype=hidden_states.dtype)
+        y_emb = self.y_embedder(class_labels)
+
+        # Ensure embeddings match hidden_states dtype
+        y_emb = y_emb.to(dtype=hidden_states.dtype)
+
+        c = t_emb + y_emb
+
+        # Patch Embed
+        grid_height, grid_width = self._get_patch_grid(hidden_states)
+        x = self.x_embedder(hidden_states)
+        if interpolate_pos_encoding:
+            pos_embed = self._interpolate_pos_encoding(x, grid_height, grid_width)
+        else:
+            expected_tokens = grid_height * grid_width
+            if self.pos_embed.shape[1] != expected_tokens:
+                raise ValueError(
+                    f"pos_embed token count {self.pos_embed.shape[1]} does not match input token count {expected_tokens}. "
+                    "Enable interpolate_pos_encoding for dynamic resolutions."
+                )
+            pos_embed = self.pos_embed.to(device=x.device, dtype=x.dtype)
+        x = x + pos_embed
+
+        # Blocks
+        for i, block in enumerate(self.blocks):
+            if self.in_context_len > 0 and i == self.in_context_start:
+                in_context_tokens = y_emb.unsqueeze(1).repeat(1, self.in_context_len, 1)
+                in_context_tokens = in_context_tokens + self.in_context_posemb.to(in_context_tokens.dtype)
+                x = torch.cat([in_context_tokens, x], dim=1)
+
+            rope = self.feat_rope if i < self.in_context_start else self.feat_rope_incontext
+
+            if self.training and self.gradient_checkpointing:
+                def custom_forward(current_x, current_c):
+                    return block(
+                        current_x,
+                        current_c,
+                        feat_rope=rope,
+                        grid_height=grid_height,
+                        grid_width=grid_width,
+                    )
+
+                x = torch.utils.checkpoint.checkpoint(
+                    custom_forward,
+                    x,
+                    c,
+                    use_reentrant=False,
+                )
+            else:
+                x = block(x, c, feat_rope=rope, grid_height=grid_height, grid_width=grid_width)
+
+        # Slice off in-context tokens
+        if self.in_context_len > 0:
+            x = x[:, self.in_context_len :]
+
+        # Final Layer
+        c = self.act_final(c)
+        shift, scale = self.adaLN_modulation_final(c).chunk(2, dim=1)
+
+        x = modulate(self.norm_final(x), shift, scale)
+        x = self.linear_final(x)
+
+        # Unpatchify
+        x = x.reshape(shape=(x.shape[0], grid_height, grid_width, self.patch_size, self.patch_size, self.out_channels))
+        x = torch.einsum("nhwpqc->nchpwq", x)
+        output = x.reshape(
+            shape=(x.shape[0], self.out_channels, grid_height * self.patch_size, grid_width * self.patch_size)
+        )
+
+        if not return_dict:
+            return (output,)
+
+        return Transformer2DModelOutput(sample=output)
+
+
+class CAFMJiTGenerator2DModel(JiTTransformer2DModel):
+    """JiT backbone with continuous adversarial flow velocity head."""
+
+    def forward(self, x: torch.Tensor, y: torch.Tensor, t: torch.Tensor) -> torch.Tensor:
+        x_pred = super().forward(
+            hidden_states=x,
+            timestep=1.0 - t,
+            class_labels=y,
+            return_dict=True,
+        ).sample
+        t_batch = t.view(-1, 1, 1, 1).clamp_min(0.05)
+        return (x - x_pred) / t_batch

CAFM-JiT-H-16-256/model_index.json

@@ -0,0 +1,1017 @@
+{
+  "_class_name": [
+    "pipeline",
+    "CAFMJiTPipeline"
+  ],
+  "_diffusers_version": "0.36.0",
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  },
+  "generator": [
+    "modeling_cafm_jit",
+    "CAFMJiTGenerator2DModel"
+  ],
+  "scheduler": [
+    "scheduling_continuous_flow",
+    "ContinuousFlowMatchScheduler"
+  ]
+}

CAFM-JiT-H-16-256/pipeline.py

@@ -0,0 +1,251 @@
+"""Hub custom pipeline: CAFMJiTPipeline.
+
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+
+
+class CAFMJiTPipeline(DiffusionPipeline):
+    model_cpu_offload_seq = "generator"
+
+    @staticmethod
+    def _coerce_scheduler(scheduler, generator):
+        if scheduler is not None and not isinstance(scheduler, (list, tuple)):
+            return scheduler
+        variant_path = getattr(generator.config, "_name_or_path", None)
+        if variant_path:
+            scheduler_dir = Path(variant_path).resolve().parent / "scheduler"
+            module_path = scheduler_dir / "scheduling_continuous_flow.py"
+            config_path = scheduler_dir / "scheduler_config.json"
+            if module_path.is_file() and config_path.is_file():
+                spec = importlib.util.spec_from_file_location("scheduling_continuous_flow", module_path)
+                if spec is not None and spec.loader is not None:
+                    module = importlib.util.module_from_spec(spec)
+                    spec.loader.exec_module(module)
+                    return module.ContinuousFlowMatchScheduler.from_pretrained(str(scheduler_dir))
+        raise ValueError("CAFMJiTPipeline could not load ContinuousFlowMatchScheduler from the variant folder.")
+
+    def __init__(
+        self,
+        generator,
+        scheduler=None,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ) -> None:
+        super().__init__()
+        scheduler = self._coerce_scheduler(scheduler, generator)
+        self.register_modules(generator=generator, scheduler=scheduler)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        labels = [label] if isinstance(label, str) else label
+        if not self.labels:
+            raise ValueError("No id2label mapping is available in this checkpoint.")
+        missing = [item for item in labels if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in labels]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        device: torch.device,
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.generator.config.sample_size)
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+        sampler: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("`num_inference_steps` must be >= 1.")
+        if output_type not in {"pil", "np", "pt"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt'.")
+        if sampler not in {"euler", "heun"}:
+            raise ValueError("sampler must be one of: 'euler', 'heun'.")
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+        latents: Optional[torch.Tensor] = None,
+        noise_scale: float = 1.0,
+    ) -> torch.Tensor:
+        if latents is not None:
+            return latents.to(device=device, dtype=dtype)
+        return (
+            randn_tensor(
+                (batch_size, self.generator.config.in_channels, height, width),
+                generator=generator,
+                device=device,
+                dtype=dtype,
+            )
+            * noise_scale
+        )
+
+    def postprocess_pixels(self, pixels: torch.Tensor, output_type: str = "pil"):
+        images_pt = ((pixels.float().clamp(-1, 1) + 1.0) / 2.0).cpu()
+        if output_type == "pt":
+            return images_pt
+        if output_type == "np":
+            return images_pt.permute(0, 2, 3, 1).numpy()
+        return self.numpy_to_pil(images_pt.permute(0, 2, 3, 1).numpy())
+
+    def _run_denoising_loop(
+        self,
+        latents: torch.Tensor,
+        class_labels_tensor: torch.Tensor,
+        batch_size: int,
+        device: torch.device,
+        num_inference_steps: int,
+        sampler: str,
+    ) -> torch.Tensor:
+        self.scheduler.set_timesteps(num_inference_steps, device=device, solver=sampler)
+        timesteps = self.scheduler.timesteps
+        self.generator.eval()
+        for t_src, t_tgt in self.progress_bar(list(zip(timesteps[:-1], timesteps[1:]))):
+            t_src_batch = t_src.expand(batch_size)
+            t_tgt_batch = t_tgt.expand(batch_size)
+            outputs = self.generator(latents, class_labels_tensor, t_src_batch)
+            if sampler == "heun":
+                latents_next = self.scheduler.step(
+                    outputs, t_src, t_tgt, latents, prediction_type="v"
+                ).prev_sample
+                outputs_next = self.generator(latents_next, class_labels_tensor, t_tgt_batch)
+                latents = self.scheduler.step(
+                    outputs,
+                    t_src,
+                    t_tgt,
+                    latents,
+                    model_output_next=outputs_next,
+                    prediction_type="v",
+                ).prev_sample
+            else:
+                latents = self.scheduler.step(
+                    outputs, t_src, t_tgt, latents, prediction_type="v"
+                ).prev_sample
+        return latents
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 100,
+        sampler: str = "heun",
+        noise_scale: float = 1.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type, sampler)
+
+        device = getattr(self, "_execution_device", None) or next(self.generator.parameters()).device
+        dtype = next(self.generator.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels, device=device)
+        batch_size = class_labels_tensor.shape[0]
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+            noise_scale=noise_scale,
+        )
+        latents = self._run_denoising_loop(
+            latents,
+            class_labels_tensor,
+            batch_size,
+            device,
+            num_inference_steps,
+            sampler,
+        )
+        image = self.postprocess_pixels(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)

CAFM-JiT-H-16-256/scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "ContinuousFlowMatchScheduler",
+  "_diffusers_version": "0.36.0",
+  "solver": "heun"
+}

CAFM-JiT-H-16-256/scheduler/scheduling_continuous_flow.py

@@ -0,0 +1,98 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import List, Optional, Tuple, Union
+
+import torch
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.schedulers.scheduling_utils import SchedulerMixin
+from diffusers.utils import BaseOutput
+
+
+@dataclass
+class ContinuousFlowMatchSchedulerOutput(BaseOutput):
+    prev_sample: torch.Tensor
+
+
+class ContinuousFlowMatchScheduler(SchedulerMixin, ConfigMixin):
+    """Flow-matching scheduler for AFM with time in [1, 0]."""
+
+    order = 2
+
+    @register_to_config
+    def __init__(self, solver: str = "euler"):
+        if solver not in {"euler", "heun"}:
+            raise ValueError("solver must be one of: 'euler', 'heun'.")
+        self.timesteps: Optional[torch.Tensor] = None
+        self.num_inference_steps: Optional[int] = None
+        self._step_index: Optional[int] = None
+
+    @property
+    def init_noise_sigma(self) -> float:
+        return 1.0
+
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Union[str, torch.device, None] = None,
+        solver: Optional[str] = None,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        self.num_inference_steps = num_inference_steps
+        if solver == "heun":
+            grid_size = (num_inference_steps // 2) + 1
+        else:
+            grid_size = num_inference_steps + 1
+        self.timesteps = torch.linspace(1.0, 0.0, grid_size, device=device, dtype=torch.float32)
+        self._step_index = 0
+        if solver is not None:
+            self.register_to_config(solver=solver)
+
+    def scale_model_input(self, sample: torch.Tensor, timestep: Union[float, torch.Tensor]) -> torch.Tensor:
+        del timestep
+        return sample
+
+    def _resolve_step_index(self, timestep: Union[float, torch.Tensor, None]) -> int:
+        if self._step_index is not None:
+            return self._step_index
+        if self.timesteps is None:
+            raise ValueError("Call `set_timesteps` before `step`.")
+        if timestep is None:
+            return 0
+        t_value = float(timestep) if not isinstance(timestep, torch.Tensor) else float(timestep.flatten()[0])
+        matches = (self.timesteps - t_value).abs() < 1e-6
+        if matches.any():
+            return int(matches.nonzero(as_tuple=False)[0].item())
+        return 0
+
+    def step(
+        self,
+        model_output: torch.Tensor,
+        timestep_src: Union[float, torch.Tensor],
+        timestep_tgt: Union[float, torch.Tensor],
+        sample: torch.Tensor,
+        model_output_next: Optional[torch.Tensor] = None,
+        prediction_type: str = "v",
+        return_dict: bool = True,
+    ) -> Union[ContinuousFlowMatchSchedulerOutput, Tuple[torch.Tensor]]:
+        if prediction_type == "x":
+            prev_sample = model_output
+        else:
+            t_src = torch.as_tensor(timestep_src, device=sample.device, dtype=sample.dtype)
+            t_tgt = torch.as_tensor(timestep_tgt, device=sample.device, dtype=sample.dtype)
+            while t_src.ndim < sample.ndim:
+                t_src = t_src.unsqueeze(-1)
+                t_tgt = t_tgt.unsqueeze(-1)
+            dt = t_src - t_tgt
+            if self.config.solver == "heun" and model_output_next is not None:
+                prev_sample = sample - dt * 0.5 * (model_output + model_output_next)
+            else:
+                prev_sample = sample - dt * model_output
+
+        step_index = self._resolve_step_index(timestep_src)
+        self._step_index = step_index + 1
+
+        if not return_dict:
+            return (prev_sample,)
+        return ContinuousFlowMatchSchedulerOutput(prev_sample=prev_sample)

CAFM-SiT-XL-2-256/generator/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "CAFMSiTGenerator2DModel",
+  "_diffusers_version": "0.36.0",
+  "input_size": 32,
+  "patch_size": 2,
+  "in_channels": 4,
+  "hidden_size": 1152,
+  "depth": 28,
+  "num_heads": 16,
+  "mlp_ratio": 4.0,
+  "learn_sigma": true,
+  "class_dropout_prob": 0.0,
+  "num_classes": 1001
+}

CAFM-SiT-XL-2-256/generator/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3530d2a4ddbca7256d97a6aa1207dd1f058d29578465b1141e04eab0db390ed
+size 2700547760

CAFM-SiT-XL-2-256/generator/modeling_cafm_sit.py

@@ -0,0 +1,252 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import math
+from dataclasses import dataclass
+from typing import Optional
+
+import numpy as np
+import torch
+import torch.nn as nn
+from timm.models.vision_transformer import Attention, Mlp, PatchEmbed
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_utils import ModelMixin
+from diffusers.utils import BaseOutput
+
+
+def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor) -> torch.Tensor:
+    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)
+
+
+@dataclass
+class SiTTransformer2DModelOutput(BaseOutput):
+    sample: torch.Tensor
+
+
+class TimestepEmbedder(nn.Module):
+    def __init__(self, hidden_size: int, frequency_embedding_size: int = 256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t: torch.Tensor, dim: int, max_period: int = 10000) -> torch.Tensor:
+        half = dim // 2
+        freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(
+            device=t.device
+        )
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t: torch.Tensor) -> torch.Tensor:
+        emb = self.timestep_embedding(t.float(), self.frequency_embedding_size)
+        weight_dtype = self.mlp[0].weight.dtype
+        return self.mlp(emb.to(dtype=weight_dtype))
+
+
+class LabelEmbedder(nn.Module):
+    def __init__(self, num_classes: int, hidden_size: int, dropout_prob: float):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        labels = torch.where(drop_ids, self.num_classes, labels)
+        return labels
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return self.embedding_table(labels)
+
+
+class SiTBlock(nn.Module):
+    def __init__(self, hidden_size: int, num_heads: int, mlp_ratio: float = 4.0, **block_kwargs):
+        super().__init__()
+        self.norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
+        self.attn = Attention(hidden_size, num_heads=num_heads, qkv_bias=True, **block_kwargs)
+        self.norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
+        mlp_hidden_dim = int(hidden_size * mlp_ratio)
+        approx_gelu = lambda: nn.GELU(approximate="tanh")
+        self.mlp = Mlp(in_features=hidden_size, hidden_features=mlp_hidden_dim, act_layer=approx_gelu, drop=0)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
+        x = x + gate_msa.unsqueeze(1) * self.attn(modulate(self.norm1(x), shift_msa, scale_msa))
+        x = x + gate_mlp.unsqueeze(1) * self.mlp(modulate(self.norm2(x), shift_mlp, scale_mlp))
+        return x
+
+
+class FinalLayer(nn.Module):
+    def __init__(self, hidden_size: int, patch_size: int, out_channels: int):
+        super().__init__()
+        self.norm_final = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
+        self.linear = nn.Linear(hidden_size, patch_size * patch_size * out_channels, bias=True)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
+        x = modulate(self.norm_final(x), shift, scale)
+        return self.linear(x)
+
+
+class SiTTransformer2DModel(ModelMixin, ConfigMixin):
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        patch_size: int = 2,
+        in_channels: int = 4,
+        hidden_size: int = 1152,
+        depth: int = 28,
+        num_heads: int = 16,
+        mlp_ratio: float = 4.0,
+        class_dropout_prob: float = 0.1,
+        num_classes: int = 1000,
+        learn_sigma: bool = True,
+    ):
+        super().__init__()
+        self.learn_sigma = learn_sigma
+        self.in_channels = in_channels
+        self.out_channels = in_channels * 2 if learn_sigma else in_channels
+        self.patch_size = patch_size
+        self.num_classes = num_classes
+
+        self.x_embedder = PatchEmbed(input_size, patch_size, in_channels, hidden_size, bias=True)
+        self.t_embedder = TimestepEmbedder(hidden_size)
+        self.y_embedder = LabelEmbedder(num_classes, hidden_size, class_dropout_prob)
+        num_patches = self.x_embedder.num_patches
+        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches, hidden_size), requires_grad=False)
+
+        self.blocks = nn.ModuleList([SiTBlock(hidden_size, num_heads, mlp_ratio=mlp_ratio) for _ in range(depth)])
+        self.final_layer = FinalLayer(hidden_size, patch_size, self.out_channels)
+        self.initialize_weights()
+
+    def initialize_weights(self) -> None:
+        def _basic_init(module: nn.Module):
+            if isinstance(module, nn.Linear):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+        pos_embed = get_2d_sincos_pos_embed(self.pos_embed.shape[-1], int(self.x_embedder.num_patches**0.5))
+        self.pos_embed.data.copy_(torch.from_numpy(pos_embed).float().unsqueeze(0))
+
+        w = self.x_embedder.proj.weight.data
+        nn.init.xavier_uniform_(w.view([w.shape[0], -1]))
+        nn.init.constant_(self.x_embedder.proj.bias, 0)
+        nn.init.normal_(self.y_embedder.embedding_table.weight, std=0.02)
+        nn.init.normal_(self.t_embedder.mlp[0].weight, std=0.02)
+        nn.init.normal_(self.t_embedder.mlp[2].weight, std=0.02)
+        for block in self.blocks:
+            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].weight, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.linear.weight, 0)
+        nn.init.constant_(self.final_layer.linear.bias, 0)
+
+    def unpatchify(self, x: torch.Tensor) -> torch.Tensor:
+        c = self.out_channels
+        p = self.x_embedder.patch_size[0]
+        h = w = int(x.shape[1] ** 0.5)
+        x = x.reshape(shape=(x.shape[0], h, w, p, p, c))
+        x = torch.einsum("nhwpqc->nchpwq", x)
+        return x.reshape(shape=(x.shape[0], c, h * p, h * p))
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.Tensor,
+        class_labels: torch.Tensor,
+        force_drop_ids: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> SiTTransformer2DModelOutput:
+        x = self.x_embedder(hidden_states) + self.pos_embed
+        t = self.t_embedder(timestep)
+        y = self.y_embedder(class_labels, self.training, force_drop_ids=force_drop_ids)
+        c = t + y
+        for block in self.blocks:
+            x = block(x, c)
+        x = self.final_layer(x, c)
+        x = self.unpatchify(x)
+        if self.learn_sigma:
+            x, _ = x.chunk(2, dim=1)
+        if not return_dict:
+            return (x,)
+        return SiTTransformer2DModelOutput(sample=x)
+
+
+def get_2d_sincos_pos_embed(embed_dim: int, grid_size: int, cls_token: bool = False, extra_tokens: int = 0):
+    grid_h = np.arange(grid_size, dtype=np.float32)
+    grid_w = np.arange(grid_size, dtype=np.float32)
+    grid = np.meshgrid(grid_w, grid_h)
+    grid = np.stack(grid, axis=0).reshape([2, 1, grid_size, grid_size])
+    pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
+    if cls_token and extra_tokens > 0:
+        pos_embed = np.concatenate([np.zeros([extra_tokens, embed_dim]), pos_embed], axis=0)
+    return pos_embed
+
+
+def get_2d_sincos_pos_embed_from_grid(embed_dim: int, grid: np.ndarray):
+    assert embed_dim % 2 == 0
+    emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0])
+    emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1])
+    return np.concatenate([emb_h, emb_w], axis=1)
+
+
+def get_1d_sincos_pos_embed_from_grid(embed_dim: int, pos: np.ndarray):
+    assert embed_dim % 2 == 0
+    omega = np.arange(embed_dim // 2, dtype=np.float64)
+    omega /= embed_dim / 2.0
+    omega = 1.0 / 10000**omega
+    pos = pos.reshape(-1)
+    out = np.einsum("m,d->md", pos, omega)
+    emb_sin = np.sin(out)
+    emb_cos = np.cos(out)
+    return np.concatenate([emb_sin, emb_cos], axis=1)
+
+
+class CAFMSiTGenerator2DModel(SiTTransformer2DModel):
+    """SiT backbone with continuous adversarial flow velocity head."""
+
+    def forward(self, x: torch.Tensor, y: torch.Tensor, t: torch.Tensor) -> torch.Tensor:
+        return -super().forward(
+            hidden_states=x,
+            timestep=1.0 - t,
+            class_labels=y,
+            return_dict=True,
+        ).sample

CAFM-SiT-XL-2-256/model_index.json

@@ -0,0 +1,1021 @@
+{
+  "_class_name": [
+    "pipeline",
+    "CAFMSiTPipeline"
+  ],
+  "_diffusers_version": "0.36.0",
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  },
+  "generator": [
+    "modeling_cafm_sit",
+    "CAFMSiTGenerator2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "scheduler": [
+    "scheduling_continuous_flow",
+    "ContinuousFlowMatchScheduler"
+  ]
+}

CAFM-SiT-XL-2-256/pipeline.py

@@ -0,0 +1,262 @@
+"""Hub custom pipeline: CAFMSiTPipeline.
+
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+
+
+class CAFMSiTPipeline(DiffusionPipeline):
+    model_cpu_offload_seq = "generator->vae"
+
+    @staticmethod
+    def _coerce_scheduler(scheduler, generator):
+        if scheduler is not None and not isinstance(scheduler, (list, tuple)):
+            return scheduler
+        variant_path = getattr(generator.config, "_name_or_path", None)
+        if variant_path:
+            scheduler_dir = Path(variant_path).resolve().parent / "scheduler"
+            module_path = scheduler_dir / "scheduling_continuous_flow.py"
+            config_path = scheduler_dir / "scheduler_config.json"
+            if module_path.is_file() and config_path.is_file():
+                spec = importlib.util.spec_from_file_location("scheduling_continuous_flow", module_path)
+                if spec is not None and spec.loader is not None:
+                    module = importlib.util.module_from_spec(spec)
+                    spec.loader.exec_module(module)
+                    return module.ContinuousFlowMatchScheduler.from_pretrained(str(scheduler_dir))
+        raise ValueError("CAFMSiTPipeline could not load ContinuousFlowMatchScheduler from the variant folder.")
+
+    def __init__(
+        self,
+        generator,
+        vae,
+        scheduler=None,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ) -> None:
+        super().__init__()
+        scheduler = self._coerce_scheduler(scheduler, generator)
+        self.register_modules(generator=generator, vae=vae, scheduler=scheduler)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def vae_scale_factor(self) -> int:
+        block_out_channels = getattr(self.vae.config, "block_out_channels", None)
+        if block_out_channels:
+            return int(2 ** (len(block_out_channels) - 1))
+        return 8
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        labels = [label] if isinstance(label, str) else label
+        if not self.labels:
+            raise ValueError("No id2label mapping is available in this checkpoint.")
+        missing = [item for item in labels if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in labels]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        device: torch.device,
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.generator.config.input_size) * self.vae_scale_factor
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+        sampler: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("`num_inference_steps` must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        if sampler not in {"euler", "heun"}:
+            raise ValueError("sampler must be one of: 'euler', 'heun'.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` must be divisible by {self.vae_scale_factor}, got ({height}, {width})."
+            )
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+        latents: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        if latents is not None:
+            return latents.to(device=device, dtype=dtype)
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        return randn_tensor(
+            (batch_size, self.generator.config.in_channels, latent_height, latent_width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+        scaling_factor = getattr(self.vae.config, "scaling_factor", 0.18215)
+        image = self.vae.decode(latents / scaling_factor).sample
+        if output_type == "pt":
+            return image
+        return self.image_processor.postprocess(image, output_type=output_type)
+
+    def _run_denoising_loop(
+        self,
+        latents: torch.Tensor,
+        class_labels_tensor: torch.Tensor,
+        batch_size: int,
+        device: torch.device,
+        num_inference_steps: int,
+        sampler: str,
+    ) -> torch.Tensor:
+        self.scheduler.set_timesteps(num_inference_steps, device=device, solver=sampler)
+        timesteps = self.scheduler.timesteps
+        self.generator.eval()
+        for t_src, t_tgt in self.progress_bar(list(zip(timesteps[:-1], timesteps[1:]))):
+            t_src_batch = t_src.expand(batch_size)
+            t_tgt_batch = t_tgt.expand(batch_size)
+            outputs = self.generator(latents, class_labels_tensor, t_src_batch)
+            if sampler == "heun":
+                latents_next = self.scheduler.step(
+                    outputs, t_src, t_tgt, latents, prediction_type="v"
+                ).prev_sample
+                outputs_next = self.generator(latents_next, class_labels_tensor, t_tgt_batch)
+                latents = self.scheduler.step(
+                    outputs,
+                    t_src,
+                    t_tgt,
+                    latents,
+                    model_output_next=outputs_next,
+                    prediction_type="v",
+                ).prev_sample
+            else:
+                latents = self.scheduler.step(
+                    outputs, t_src, t_tgt, latents, prediction_type="v"
+                ).prev_sample
+        return latents
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 250,
+        sampler: str = "heun",
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type, sampler)
+
+        device = getattr(self, "_execution_device", None) or next(self.generator.parameters()).device
+        dtype = next(self.generator.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels, device=device)
+        batch_size = class_labels_tensor.shape[0]
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+        )
+        latents = self._run_denoising_loop(
+            latents,
+            class_labels_tensor,
+            batch_size,
+            device,
+            num_inference_steps,
+            sampler,
+        )
+        image = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)

CAFM-SiT-XL-2-256/scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "ContinuousFlowMatchScheduler",
+  "_diffusers_version": "0.36.0",
+  "solver": "heun"
+}

CAFM-SiT-XL-2-256/scheduler/scheduling_continuous_flow.py

@@ -0,0 +1,98 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import List, Optional, Tuple, Union
+
+import torch
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.schedulers.scheduling_utils import SchedulerMixin
+from diffusers.utils import BaseOutput
+
+
+@dataclass
+class ContinuousFlowMatchSchedulerOutput(BaseOutput):
+    prev_sample: torch.Tensor
+
+
+class ContinuousFlowMatchScheduler(SchedulerMixin, ConfigMixin):
+    """Flow-matching scheduler for AFM with time in [1, 0]."""
+
+    order = 2
+
+    @register_to_config
+    def __init__(self, solver: str = "euler"):
+        if solver not in {"euler", "heun"}:
+            raise ValueError("solver must be one of: 'euler', 'heun'.")
+        self.timesteps: Optional[torch.Tensor] = None
+        self.num_inference_steps: Optional[int] = None
+        self._step_index: Optional[int] = None
+
+    @property
+    def init_noise_sigma(self) -> float:
+        return 1.0
+
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Union[str, torch.device, None] = None,
+        solver: Optional[str] = None,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        self.num_inference_steps = num_inference_steps
+        if solver == "heun":
+            grid_size = (num_inference_steps // 2) + 1
+        else:
+            grid_size = num_inference_steps + 1
+        self.timesteps = torch.linspace(1.0, 0.0, grid_size, device=device, dtype=torch.float32)
+        self._step_index = 0
+        if solver is not None:
+            self.register_to_config(solver=solver)
+
+    def scale_model_input(self, sample: torch.Tensor, timestep: Union[float, torch.Tensor]) -> torch.Tensor:
+        del timestep
+        return sample
+
+    def _resolve_step_index(self, timestep: Union[float, torch.Tensor, None]) -> int:
+        if self._step_index is not None:
+            return self._step_index
+        if self.timesteps is None:
+            raise ValueError("Call `set_timesteps` before `step`.")
+        if timestep is None:
+            return 0
+        t_value = float(timestep) if not isinstance(timestep, torch.Tensor) else float(timestep.flatten()[0])
+        matches = (self.timesteps - t_value).abs() < 1e-6
+        if matches.any():
+            return int(matches.nonzero(as_tuple=False)[0].item())
+        return 0
+
+    def step(
+        self,
+        model_output: torch.Tensor,
+        timestep_src: Union[float, torch.Tensor],
+        timestep_tgt: Union[float, torch.Tensor],
+        sample: torch.Tensor,
+        model_output_next: Optional[torch.Tensor] = None,
+        prediction_type: str = "v",
+        return_dict: bool = True,
+    ) -> Union[ContinuousFlowMatchSchedulerOutput, Tuple[torch.Tensor]]:
+        if prediction_type == "x":
+            prev_sample = model_output
+        else:
+            t_src = torch.as_tensor(timestep_src, device=sample.device, dtype=sample.dtype)
+            t_tgt = torch.as_tensor(timestep_tgt, device=sample.device, dtype=sample.dtype)
+            while t_src.ndim < sample.ndim:
+                t_src = t_src.unsqueeze(-1)
+                t_tgt = t_tgt.unsqueeze(-1)
+            dt = t_src - t_tgt
+            if self.config.solver == "heun" and model_output_next is not None:
+                prev_sample = sample - dt * 0.5 * (model_output + model_output_next)
+            else:
+                prev_sample = sample - dt * model_output
+
+        step_index = self._resolve_step_index(timestep_src)
+        self._step_index = step_index + 1
+
+        if not return_dict:
+            return (prev_sample,)
+        return ContinuousFlowMatchSchedulerOutput(prev_sample=prev_sample)

CAFM-SiT-XL-2-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-mse",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

CAFM-SiT-XL-2-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+size 334643268

CAFM-Z-Image-T2I/model_index.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": [
+    "pipeline",
+    "CAFMZImagePipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "transformer": [
+    "diffusers",
+    "ZImageTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3ForCausalLM"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ]
+}

CAFM-Z-Image-T2I/pipeline.py

@@ -0,0 +1,204 @@
+"""Hub custom pipeline: CAFMZImagePipeline.
+
+Continuous adversarial flow sampling for Tongyi-MAI/Z-Image T2I checkpoints.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+from __future__ import annotations
+
+from typing import List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline
+from diffusers.utils.torch_utils import randn_tensor
+from einops import rearrange
+from transformers import AutoTokenizer, PreTrainedModel
+
+
+class CAFMZImagePipelineOutput:
+    def __init__(self, images):
+        self.images = images
+
+
+class CAFMZImagePipeline(DiffusionPipeline):
+    model_cpu_offload_seq = "text_encoder->transformer->vae"
+    _optional_components = ["scheduler"]
+
+    def __init__(
+        self,
+        transformer,
+        vae,
+        text_encoder: PreTrainedModel,
+        tokenizer: AutoTokenizer,
+        scheduler=None,
+        timestep_shift: float = 1.0 / 3.0,
+        default_sampler: str = "euler",
+    ) -> None:
+        super().__init__()
+        modules = {
+            "transformer": transformer,
+            "vae": vae,
+            "text_encoder": text_encoder,
+            "tokenizer": tokenizer,
+        }
+        if scheduler is not None and not isinstance(scheduler, (list, tuple)):
+            modules["scheduler"] = scheduler
+        self.register_modules(**modules)
+        self.register_to_config(timestep_shift=float(timestep_shift))
+        self.vae_scale_factor = (
+            2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self.vae, "config") else 8
+        )
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor * 2)
+
+    @staticmethod
+    def shift_timesteps(timesteps: torch.Tensor, shift: float) -> torch.Tensor:
+        return (timesteps * shift) / (1 + (shift - 1) * timesteps)
+
+    def encode_prompt(
+        self,
+        prompt: Union[str, List[str]],
+        device: torch.device,
+        max_sequence_length: int = 512,
+    ) -> List[torch.Tensor]:
+        prompts = [prompt] if isinstance(prompt, str) else list(prompt)
+        formatted = []
+        for prompt_item in prompts:
+            messages = [{"role": "user", "content": prompt_item}]
+            formatted.append(
+                self.tokenizer.apply_chat_template(
+                    messages,
+                    tokenize=False,
+                    add_generation_prompt=True,
+                    enable_thinking=True,
+                )
+            )
+        text_inputs = self.tokenizer(
+            formatted,
+            padding="max_length",
+            max_length=max_sequence_length,
+            truncation=True,
+            return_tensors="pt",
+        )
+        text_input_ids = text_inputs.input_ids.to(device)
+        prompt_masks = text_inputs.attention_mask.to(device).bool()
+        prompt_embeds = self.text_encoder(
+            input_ids=text_input_ids,
+            attention_mask=prompt_masks,
+            output_hidden_states=True,
+        ).hidden_states[-2]
+        return [prompt_embeds[i][prompt_masks[i]] for i in range(len(prompt_embeds))]
+
+    def _latent_hw(self, height: int, width: int) -> tuple[int, int]:
+        height = 2 * (int(height) // (self.vae_scale_factor * 2))
+        width = 2 * (int(width) // (self.vae_scale_factor * 2))
+        return height, width
+
+    def prepare_noises(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+    ) -> List[torch.Tensor]:
+        latent_height, latent_width = self._latent_hw(height, width)
+        in_channels = int(self.transformer.config.in_channels)
+        noises = []
+        for index in range(batch_size):
+            gen = generator[index] if isinstance(generator, list) else generator
+            noise = randn_tensor(
+                (in_channels, 1, latent_height, latent_width),
+                generator=gen,
+                device=device,
+                dtype=dtype,
+            )
+            noises.append(noise)
+        return noises
+
+    def decode_latents(self, latents: List[torch.Tensor], output_type: str = "pil"):
+        scale = self.vae.config.scaling_factor
+        shift = self.vae.config.shift_factor
+        device = getattr(self, "_execution_device", next(self.vae.parameters()).device)
+        vae_dtype = self.vae.dtype
+        images = []
+        for latent in latents:
+            latent = rearrange(latent, "c f h w -> f c h w").to(device=device, dtype=vae_dtype)
+            latent = latent / scale + shift
+            sample = self.vae.decode(latent).sample
+            images.append(sample.squeeze(0).float())
+        stacked = torch.stack(images, dim=0)
+        if output_type == "pt":
+            return stacked
+        if output_type == "np":
+            return self.image_processor.postprocess(stacked, output_type="np")
+        return self.image_processor.postprocess(stacked, output_type="pil")
+
+    def _run_denoising_loop(
+        self,
+        latents: List[torch.Tensor],
+        text_embeds: List[torch.Tensor],
+        num_inference_steps: int,
+        sampler: str,
+    ) -> List[torch.Tensor]:
+        device = latents[0].device
+        dtype = latents[0].dtype
+        timesteps = torch.linspace(0.0, 1.0, num_inference_steps + 1, device=device, dtype=dtype)
+        timesteps = self.shift_timesteps(timesteps, self.config.timestep_shift)
+
+        self.transformer.eval()
+        for t_src, t_tgt in self.progress_bar(list(zip(timesteps[:-1], timesteps[1:]))):
+            dt = t_tgt - t_src
+            t_src_batch = t_src.expand(len(latents)).to(dtype=dtype)
+            outputs = self.transformer(latents, t_src_batch, text_embeds, return_dict=True).sample
+            if sampler == "heun":
+                latents_next = [x_t + dt * velocity for x_t, velocity in zip(latents, outputs)]
+                t_tgt_batch = t_tgt.expand(len(latents)).to(dtype=dtype)
+                outputs_next = self.transformer(latents_next, t_tgt_batch, text_embeds, return_dict=True).sample
+                latents = [
+                    x_t + dt * 0.5 * (velocity + velocity_next)
+                    for x_t, velocity, velocity_next in zip(latents, outputs, outputs_next)
+                ]
+            else:
+                latents = [x_t + dt * velocity for x_t, velocity in zip(latents, outputs)]
+        return latents
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        prompt: Union[str, List[str]],
+        height: int = 512,
+        width: int = 512,
+        num_inference_steps: int = 25,
+        sampler: str = "euler",
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        max_sequence_length: int = 512,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[CAFMZImagePipelineOutput, Tuple]:
+        if sampler not in {"euler", "heun"}:
+            raise ValueError("sampler must be one of: 'euler', 'heun'.")
+
+        vae_scale = self.vae_scale_factor * 2
+        if height % vae_scale != 0 or width % vae_scale != 0:
+            raise ValueError(f"height and width must be divisible by {vae_scale}, got ({height}, {width}).")
+
+        device = getattr(self, "_execution_device", None) or next(self.transformer.parameters()).device
+        dtype = getattr(self.transformer, "dtype", torch.float32)
+        prompts = [prompt] if isinstance(prompt, str) else list(prompt)
+        text_embeds = self.encode_prompt(prompts, device=device, max_sequence_length=max_sequence_length)
+        latents = self.prepare_noises(
+            batch_size=len(prompts),
+            height=height,
+            width=width,
+            dtype=dtype,
+            device=device,
+            generator=generator,
+        )
+        latents = self._run_denoising_loop(latents, text_embeds, num_inference_steps, sampler)
+        images = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (images,)
+        return CAFMZImagePipelineOutput(images=images)

CAFM-Z-Image-T2I/scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.37.0.dev0",
+  "num_train_timesteps": 1000,
+  "use_dynamic_shifting": false,
+  "shift": 6.0
+}

CAFM-Z-Image-T2I/text_encoder/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

CAFM-Z-Image-T2I/text_encoder/generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "pad_token_id": 151643,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.51.0"
+}

CAFM-Z-Image-T2I/text_encoder/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328a91d3122359d5547f9d79521205bc0a46e1f79a792dfe650e99fc2d651223
+size 3957900840

CAFM-Z-Image-T2I/text_encoder/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd087b316306a68c562436b5492edbcf6e16c6dba3a1308279caa5a58e21ca5
+size 3987450520

CAFM-Z-Image-T2I/text_encoder/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca841ee75b9c61267c0c6148fd8d096d3d21b6d3e161256a9b878154f91fc52
+size 99630640

CAFM-Z-Image-T2I/text_encoder/model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

CAFM-Z-Image-T2I/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

CAFM-Z-Image-T2I/tokenizer/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

CAFM-Z-Image-T2I/transformer/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "ZImageTransformer2DModel",
+  "_diffusers_version": "0.37.0.dev0",
+  "all_f_patch_size": [
+    1
+  ],
+  "all_patch_size": [
+    2
+  ],
+  "axes_dims": [
+    32,
+    48,
+    48
+  ],
+  "axes_lens": [
+    1536,
+    512,
+    512
+  ],
+  "cap_feat_dim": 2560,
+  "dim": 3840,
+  "in_channels": 16,
+  "n_heads": 30,
+  "n_kv_heads": 30,
+  "n_layers": 30,
+  "n_refiner_layers": 2,
+  "norm_eps": 1e-05,
+  "qk_norm": true,
+  "rope_theta": 256.0,
+  "siglip_feat_dim": null,
+  "t_scale": 1000.0
+}

CAFM-Z-Image-T2I/transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd5df7768856215812af84d5cc785ba9d84c6d8c84e6939c7ccf30a2e0d2425
+size 9973727144

CAFM-Z-Image-T2I/transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d5fb75ca504b2d669a33af9380b68e0c1632ecddbfca85f82631958a4b81b1
+size 2336146728

CAFM-Z-Image-T2I/transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,528 @@
+{
+  "metadata": {
+    "total_size": 12309817472
+  },
+  "weight_map": {
+    "all_final_layer.2-1.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "all_final_layer.2-1.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "all_final_layer.2-1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "all_final_layer.2-1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "all_x_embedder.2-1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "all_x_embedder.2-1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "cap_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "cap_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "cap_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "cap_pad_token": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.23.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.3.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_pad_token": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

CAFM-Z-Image-T2I/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "../checkpoints/flux-dev",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.3611,
+  "shift_factor": 0.1159,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

CAFM-Z-Image-T2I/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
+size 167666902

README.md

@@ -0,0 +1,99 @@
+---
+license: mit
+library_name: diffusers
+pipeline_tag: text-to-image
+tags:
+- diffusers
+- cafm
+- continuous-adversarial-flow-models
+- class-conditional
+- imagenet
+- text-to-image
+- z-image
+inference: true
+widget:
+- output:
+    url: CAFM-JiT-H-16-256/demo.png
+language:
+- en
+---
+
+# BiliSakura/CAFM-diffusers
+
+Self-contained [Continuous Adversarial Flow Models](https://arxiv.org/abs/2604.11521) checkpoints for Hugging Face diffusers.
+
+Converted from `ByteDance-Seed/Adversarial-Flow-Models` using `libs/AFM-diffusers/scripts/convert_cafm_to_diffusers.py`.
+Z-Image weights are bundled self-contained under `CAFM-Z-Image-T2I/`.
+
+## Demo
+
+`CAFM-JiT-H-16-256` — class **207** (*golden retriever*), seed **0**, 100 NFE (Heun):
+
+<p align="center">
+  <img src="CAFM-JiT-H-16-256/demo.png" alt="CAFM-JiT-H-16-256 demo (class 207, seed 0)" width="256"/>
+</p>
+
+Each variant folder includes `demo.png` generated with the same prompt settings.
+
+## Benchmark results (ImageNet 256×256)
+
+| Model | Space | NFE | FID | Checkpoint |
+| --- | --- | --- | --- | --- |
+| CAFM JiT-H/16 | pixel | 100 | 1.80 | `CAFM-JiT-H-16-256/` |
+| CAFM SiT-XL/2 | latent | 250 | 1.53 | `CAFM-SiT-XL-2-256/` |
+| CAFM Z-Image | latent T2I | 25 | — | `CAFM-Z-Image-T2I/` |
+
+## Available checkpoints
+
+| Variant | Backbone | Steps | Solver |
+| --- | --- | ---: | --- |
+| `CAFM-JiT-H-16-256/` | JIT | 100 | heun |
+| `CAFM-SiT-XL-2-256/` | SIT | 250 | heun |
+| `CAFM-Z-Image-T2I/` | Z-IMAGE | 25 | euler |
+
+## Inference
+
+### ImageNet class-conditional (JiT / SiT)
+
+```python
+from pathlib import Path
+import torch
+from diffusers import DiffusionPipeline
+
+model_dir = Path("./CAFM-SiT-XL-2-256")
+pipe = DiffusionPipeline.from_pretrained(
+    str(model_dir),
+    local_files_only=True,
+    custom_pipeline=str(model_dir / "pipeline.py"),
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+).to("cuda")
+
+image = pipe(class_labels="golden retriever", num_inference_steps=250, sampler="heun").images[0]
+```
+
+### Text-to-image (Z-Image)
+
+```python
+from pathlib import Path
+import torch
+from diffusers import DiffusionPipeline
+
+model_dir = Path("./CAFM-Z-Image-T2I")
+pipe = DiffusionPipeline.from_pretrained(
+    str(model_dir),
+    local_files_only=True,
+    custom_pipeline=str(model_dir / "pipeline.py"),
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+)
+pipe.enable_model_cpu_offload()  # recommended for single-GPU inference
+
+image = pipe(
+    prompt="A golden retriever sitting in a sunny park, photo realistic.",
+    height=512,
+    width=512,
+    num_inference_steps=25,
+    sampler="euler",
+).images[0]
+```