Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+GAT-XL-2-256/demo.png filter=lfs diff=lfs merge=lfs -text
+GAT-XL-2-256/demo_bf16.png filter=lfs diff=lfs merge=lfs -text

GAT-XL-2-256/generator/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "GATGenerator",
+  "_diffusers_version": "0.38.0",
+  "class_dropout_prob": 0.0,
+  "depth": 28,
+  "fused_attn": true,
+  "hidden_size": 1152,
+  "in_channels": 4,
+  "input_size": 32,
+  "latent_size": 64,
+  "mlp_ratio": 4.0,
+  "num_classes": 1000,
+  "num_heads": 16,
+  "patch_size": 2,
+  "projector_dim": 2048,
+  "qk_norm": true,
+  "z_dims": [
+    768
+  ]
+}

GAT-XL-2-256/generator/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685b233351d3a1b28b6851394bd67d877eef5295fa1387480041239b4aed8e21
+size 2413796224

GAT-XL-2-256/generator/modeling_gat.py

@@ -0,0 +1,503 @@
+"""Hub custom module: GATGenerator for Generative Adversarial Transformers."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from math import pi
+from typing import Optional, Type
+
+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_utils import ModelMixin
+from diffusers.utils import BaseOutput
+from einops import rearrange, repeat
+from timm.models.vision_transformer import Mlp, PatchEmbed
+
+class EqualLinear(nn.Module):
+    def __init__(self, in_dim, out_dim, bias=True, bias_init=0, lr_mult=1):
+        super().__init__()
+        self.weight = nn.Parameter(torch.zeros(out_dim, in_dim))
+        if bias:
+            self.bias = nn.Parameter(torch.zeros(out_dim).fill_(bias_init))
+        else:
+            self.register_parameter("bias", None)
+        self.lr_mult = lr_mult
+        self.init_weight(lr_mult=lr_mult)
+
+    def init_weight(self, lr_mult):
+        nn.init.xavier_uniform_(self.weight, gain=1 / lr_mult)
+        if self.bias is not None:
+            nn.init.constant_(self.bias, 0)
+
+    def forward(self, x):
+        bias = self.bias * self.lr_mult if self.bias is not None else None
+        return torch.nn.functional.linear(x, self.weight * self.lr_mult, bias=bias)
+
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim: int,
+        num_heads: int = 8,
+        qkv_bias: bool = False,
+        qk_norm: bool = False,
+        proj_bias: bool = True,
+        attn_drop: float = 0.0,
+        proj_drop: float = 0.0,
+        norm_layer: Type[nn.Module] = nn.RMSNorm,
+        fused_attn: bool = False,
+    ) -> None:
+        super().__init__()
+        assert dim % num_heads == 0
+        self.num_heads = num_heads
+        self.head_dim = dim // num_heads
+        self.scale = self.head_dim ** -0.5
+        self.fused_attn = fused_attn
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.q_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
+        self.k_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim, bias=proj_bias)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+    def forward(self, x, rope=None, return_attention=False):
+        bsz, num_tokens, channels = x.shape
+        qkv = self.qkv(x).reshape(bsz, num_tokens, 3, self.num_heads, self.head_dim)
+        q, k, v = qkv.permute(2, 0, 3, 1, 4).unbind(0)
+
+        q = self.q_norm(q)
+        k = self.k_norm(k)
+        if rope is not None:
+            q = rope(q)
+            k = rope(k)
+
+        if self.fused_attn and not return_attention:
+            x = torch.nn.functional.scaled_dot_product_attention(
+                q,
+                k,
+                v,
+                dropout_p=self.attn_drop.p if self.training else 0.0,
+            )
+            attn = None
+        else:
+            attn = (q * self.scale) @ k.transpose(-2, -1)
+            attn = self.attn_drop(attn.softmax(dim=-1))
+            x = attn @ v
+
+        x = x.transpose(1, 2).reshape(bsz, num_tokens, channels)
+        x = self.proj_drop(self.proj(x))
+        if return_attention:
+            return x, attn
+        return x
+
+
+class FourierFeature(nn.Module):
+    def __init__(self, hidden_size, resolution=16):
+        super().__init__()
+        self.linear = nn.Linear(2, hidden_size)
+        y = torch.linspace(-1, 1, steps=resolution)
+        x = torch.linspace(-1, 1, steps=resolution)
+        yy, xx = torch.meshgrid(y, x, indexing="ij")
+        coords = torch.stack([xx, yy], dim=-1).view(1, resolution * resolution, 2)
+        self.register_buffer("coords", coords)
+
+    def reset_parameters(self):
+        nn.init.uniform_(self.linear.weight, -np.sqrt(9 / 2), np.sqrt(9 / 2))
+
+    def forward(self, x):
+        return torch.sin(self.linear(self.coords.to(x.dtype))).repeat(x.shape[0], 1, 1)
+
+
+class SwiGLUFFN(nn.Module):
+    def __init__(self, in_features: int, hidden_features: int | None = None, out_features: int | None = None, bias: bool = True):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.w12 = nn.Linear(in_features, 2 * hidden_features, bias=bias)
+        self.w3 = nn.Linear(hidden_features, out_features, bias=bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x12 = self.w12(x)
+        x1, x2 = x12.chunk(2, dim=-1)
+        hidden = F.silu(x1) * x2
+        return self.w3(hidden)
+
+
+def broadcat(tensors, dim=-1):
+    num_tensors = len(tensors)
+    shape_lens = set(list(map(lambda t: len(t.shape), tensors)))
+    assert len(shape_lens) == 1, "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(*map(lambda t: list(t.shape), tensors)))
+    expandable_dims = [(i, val) for i, val in enumerate(dims) if i != dim]
+    assert all([*map(lambda t: len(set(t[1])) <= 2, expandable_dims)]), "invalid dimensions for broadcastable concatentation"
+    max_dims = list(map(lambda t: (t[0], max(t[1])), expandable_dims))
+    expanded_dims = list(map(lambda t: (t[0], (t[1],) * num_tensors), max_dims))
+    expanded_dims.insert(dim, (dim, dims[dim]))
+    expandable_shapes = list(zip(*map(lambda t: t[1], expanded_dims)))
+    tensors = list(map(lambda t: t[0].expand(*t[1]), zip(tensors, expandable_shapes)))
+    return torch.cat(tensors, dim=dim)
+
+
+def rotate_half(x):
+    x = rearrange(x, "... (d r) -> ... d r", r=2)
+    x1, x2 = x.unbind(dim=-1)
+    x = torch.stack((-x2, x1), dim=-1)
+    return rearrange(x, "... d r -> ... (d r)")
+
+
+class VisionRotaryEmbeddingFast(nn.Module):
+    def __init__(
+        self,
+        dim,
+        pt_seq_len=16,
+        ft_seq_len=None,
+        custom_freqs=None,
+        freqs_for="lang",
+        theta=10000,
+        max_freq=10,
+        num_freqs=1,
+    ):
+        super().__init__()
+        self.pt_seq_len = pt_seq_len
+
+        if custom_freqs:
+            freqs = custom_freqs
+        elif freqs_for == "lang":
+            freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[:(dim // 2)].float() / dim))
+        elif freqs_for == "pixel":
+            freqs = torch.linspace(1.0, max_freq / 2, dim // 2) * pi
+        elif freqs_for == "constant":
+            freqs = torch.ones(num_freqs).float()
+        else:
+            raise ValueError(f"unknown modality {freqs_for}")
+
+        if ft_seq_len is None:
+            ft_seq_len = pt_seq_len
+        t = torch.arange(ft_seq_len) / ft_seq_len * pt_seq_len
+
+        freqs = torch.einsum("..., f -> ... f", t, freqs)
+        freqs = repeat(freqs, "... n -> ... (n r)", r=2)
+        freqs = broadcat((freqs[:, None, :], freqs[None, :, :]), dim=-1)
+
+        freqs_cos = freqs.cos().view(-1, freqs.shape[-1])
+        freqs_sin = freqs.sin().view(-1, freqs.shape[-1])
+
+        self.register_buffer("freqs_cos", freqs_cos)
+        self.register_buffer("freqs_sin", freqs_sin)
+
+    def forward(self, t):
+        t_spatial = t[:, :, -self.pt_seq_len**2 :]
+        t_pe = t_spatial * self.freqs_cos + rotate_half(t_spatial) * self.freqs_sin
+        return torch.cat([t[:, :, : -self.pt_seq_len**2], t_pe], dim=2)
+
+
+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):
+    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, pos):
+    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)
+
+
+def normalize_2nd_moment(x, dim=1, eps=1e-8):
+    return x * (x.square().mean(dim=dim, keepdim=True) + eps).rsqrt()
+
+
+def modulate(x, scale, shift=None):
+    if shift is None:
+        return x * (1 + scale.unsqueeze(1))
+    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)
+
+
+@dataclass
+class GATGeneratorOutput(BaseOutput):
+    sample: torch.Tensor
+
+
+class _GenLabelEmbedder(nn.Module):
+    def __init__(self, num_classes, hidden_size, dropout_prob):
+        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 forward(self, labels, train):
+        return self.embedding_table(labels)
+
+
+class GATBlock(nn.Module):
+    def __init__(self, hidden_size, w_dim, num_heads, mlp_ratio=4.0, **block_kwargs):
+        super().__init__()
+        self.norm1 = nn.RMSNorm(hidden_size, elementwise_affine=False, eps=1e-6)
+        self.attn = Attention(
+            hidden_size,
+            num_heads=num_heads,
+            qkv_bias=True,
+            qk_norm=block_kwargs["qk_norm"],
+            fused_attn=block_kwargs["fused_attn"],
+        )
+        self.norm2 = nn.RMSNorm(hidden_size, elementwise_affine=False, eps=1e-6)
+        mlp_hidden_dim = int(hidden_size * mlp_ratio)
+        approx_gelu = lambda: nn.GELU(approximate="tanh")
+        use_swiglu = True
+        if use_swiglu:
+            self.mlp = SwiGLUFFN(hidden_size, int(2 / 3 * mlp_hidden_dim))
+        else:
+            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(w_dim, 4 * hidden_size, bias=True),
+        )
+
+    def forward(self, x, c, feat_rope=None):
+        scale_msa, gate_msa, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(4, dim=1)
+        x = x + gate_msa.unsqueeze(1) * self.attn(modulate(self.norm1(x), scale_msa), rope=feat_rope)
+        x = x + gate_mlp.unsqueeze(1) * self.mlp(modulate(self.norm2(x), scale_mlp))
+        return x
+
+
+class FinalLayer(nn.Module):
+    def __init__(self, hidden_size, w_dim, patch_size, out_channels):
+        super().__init__()
+        self.norm_final = nn.RMSNorm(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(w_dim, hidden_size, bias=True),
+        )
+
+    def forward(self, x, c):
+        scale = self.adaLN_modulation(c)
+        x = modulate(self.norm_final(x), scale)
+        return self.linear(x)
+
+
+class GATGenerator(ModelMixin, ConfigMixin):
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        patch_size: int = 2,
+        in_channels: int = 4,
+        latent_size: int = 64,
+        hidden_size: int = 1152,
+        depth: int = 28,
+        num_heads: int = 16,
+        mlp_ratio: float = 4.0,
+        class_dropout_prob: float = 0.0,
+        num_classes: int = 1000,
+        z_dims: Optional[list[int]] = None,
+        projector_dim: int = 2048,
+        fused_attn: bool = True,
+        qk_norm: bool = True,
+    ):
+        super().__init__()
+        z_dims = z_dims or [768]
+        block_kwargs = {"fused_attn": fused_attn, "qk_norm": qk_norm}
+
+        self.input_size = input_size
+        self.in_channels = in_channels
+        self.out_channels = in_channels
+        self.patch_size = patch_size
+        self.num_heads = num_heads
+        self.num_classes = num_classes
+        self.z_dims = z_dims
+        self.hidden_size = hidden_size
+        self.latent_size = latent_size
+        self.depth = depth
+        w_dim = self.hidden_size
+
+        self.x_embedder = PatchEmbed(input_size, patch_size, in_channels, hidden_size, bias=True)
+        self.y_embedder = _GenLabelEmbedder(num_classes, latent_size, class_dropout_prob)
+        self.num_patches = (input_size // patch_size) ** 2
+
+        st_resolution = self.input_size // self.patch_size
+        self.num_st_patches = st_resolution**2
+
+        self.use_fourierfeat = False
+        if self.use_fourierfeat:
+            self.pos_embed = FourierFeature(hidden_size, resolution=st_resolution)
+        else:
+            self.pos_embed = nn.Parameter(torch.zeros(1, st_resolution**2, hidden_size), requires_grad=False)
+
+        self.use_rope = True
+        if self.use_rope:
+            half_head_dim = hidden_size // num_heads // 2
+            hw_seq_len = input_size // patch_size
+            self.feat_rope = VisionRotaryEmbeddingFast(dim=half_head_dim, pt_seq_len=hw_seq_len)
+        else:
+            self.feat_rope = None
+
+        self.latent_embedder = nn.Sequential(
+            EqualLinear(latent_size * 2, w_dim, lr_mult=0.01),
+            nn.SiLU(),
+            EqualLinear(w_dim, w_dim, lr_mult=0.01),
+        )
+
+        rgb_every = self.depth // 4
+        self.rgb_indice = [(i + 1) * rgb_every - 1 for i in range(depth // rgb_every)]
+
+        self.blocks = nn.ModuleList(
+            [GATBlock(hidden_size, w_dim, num_heads, mlp_ratio=mlp_ratio, **block_kwargs) for _ in range(depth)]
+        )
+        self.final_layers = nn.ModuleList(
+            [FinalLayer(hidden_size, w_dim, patch_size, self.out_channels) for _ in range(len(self.rgb_indice))]
+        )
+
+        self.initialize_weights()
+
+        self.w_avg_beta = 0.995
+        self.register_buffer("w_avg", torch.zeros([num_classes, w_dim]))
+
+    def initialize_weights(self):
+        def _basic_init(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)
+            if isinstance(module, nn.Conv2d):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+
+        if self.use_fourierfeat:
+            self.pos_embed.reset_parameters()
+        else:
+            pos_embed = get_2d_sincos_pos_embed(self.pos_embed.shape[-1], int(self.num_st_patches**0.5))
+            self.pos_embed.data.copy_(torch.from_numpy(pos_embed).float().unsqueeze(0))
+
+        nn.init.normal_(self.y_embedder.embedding_table.weight, std=0.02)
+
+        layer_gain = 1e-1
+        for block in self.blocks:
+            nn.init.xavier_uniform_(block.adaLN_modulation[-1].weight, gain=layer_gain)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+
+        for final_layer in self.final_layers:
+            nn.init.xavier_uniform_(final_layer.adaLN_modulation[-1].weight, gain=layer_gain)
+            nn.init.constant_(final_layer.adaLN_modulation[-1].bias, 0)
+
+        if isinstance(self.x_embedder, PatchEmbed):
+            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)
+
+    def unpatchify(self, x, patch_size=None):
+        c = x.shape[-1] // (self.patch_size**2)
+        p = self.patch_size
+        h = w = int(x.shape[1] ** 0.5)
+        assert h * w == x.shape[1]
+        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, w * p))
+
+    def ckpt_wrapper(self, module):
+        def ckpt_forward(*inputs):
+            return module(*inputs)
+
+        return ckpt_forward
+
+    def forward(
+        self,
+        x,
+        y,
+        z,
+        guidance_scale=1.0,
+        update_ema=False,
+        truncation_psi=0.0,
+        multiscale=False,
+        return_dict: bool = False,
+    ):
+        x = self.x_embedder(x) * 0.0 + self.pos_embed(z) if self.use_fourierfeat else self.pos_embed + self.x_embedder(x) * 0.0
+
+        y_idx = y
+        y = self.y_embedder(y, self.training)
+        c = torch.cat([normalize_2nd_moment(y.squeeze(1)), normalize_2nd_moment(z)], dim=1)
+        c = self.latent_embedder(c)
+
+        if truncation_psi != 0.0:
+            c = c.lerp(self.w_avg[y_idx], truncation_psi)
+
+        if self.w_avg_beta is not None and update_ema:
+            unique_labels = y_idx.unique()
+            for label in unique_labels:
+                mask = y_idx.squeeze() == label
+                avg_c = c[mask].mean(dim=0)
+                self.w_avg[label].copy_(avg_c.detach().lerp(self.w_avg[label].to(c.dtype), self.w_avg_beta))
+
+        if torch.is_tensor(guidance_scale):
+            scales = guidance_scale
+        else:
+            scales = torch.full((y.shape[0],), guidance_scale, device=y.device, dtype=z.dtype)
+
+        if (scales != 1.0).any():
+            indices = torch.arange(self.num_classes).to(y_idx.device)
+            y_null = self.y_embedder(indices, self.training)
+            y_null = y_null.unsqueeze(0).repeat(z.shape[0], 1, 1)
+            z_null = z.unsqueeze(1).repeat(1, self.num_classes, 1)
+            w_null = torch.cat([normalize_2nd_moment(y_null), normalize_2nd_moment(z_null)], dim=-1)
+            w_null = self.latent_embedder(w_null).detach().mean(dim=1)
+            c = w_null + scales.unsqueeze(1) * (c - w_null)
+
+        xs = []
+        for block in self.blocks:
+            x = torch.utils.checkpoint.checkpoint(
+                self.ckpt_wrapper(block), x, c, self.feat_rope, use_reentrant=False
+            )
+            xs.append(x)
+
+        self.recent_x_std = x.std()
+
+        rgbs = []
+        rgb_accum = 0
+        for i, final_layer in zip(self.rgb_indice, self.final_layers):
+            rgb = final_layer(xs[i], c)
+            rgb_accum = rgb_accum + self.unpatchify(rgb)
+            rgbs.append(rgb_accum)
+
+        if multiscale:
+            output = torch.stack(rgbs, dim=0)
+        else:
+            output = rgbs[-1]
+
+        if not return_dict:
+            return (output,)
+        return GATGeneratorOutput(sample=output)
+

GAT-XL-2-256/model_index.json

@@ -0,0 +1,1018 @@
+{
+  "_class_name": [
+    "pipeline",
+    "GATPipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "generator": [
+    "modeling_gat",
+    "GATGenerator"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "truncation_psi": 0.3,
+  "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"
+  }
+}

GAT-XL-2-256/pipeline.py

@@ -0,0 +1,211 @@
+"""Hub custom pipeline: GATPipeline.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.models import AutoencoderKL
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+
+
+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()}
+
+
+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()}
+
+
+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()))
+
+
+def _normalize_class_labels(
+    class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+    *,
+    device: torch.device,
+    label2id: Dict[str, int],
+) -> 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):
+        if not label2id:
+            raise ValueError("No English labels loaded. Provide `id2label` in the pipeline config.")
+        if class_labels not in label2id:
+            raise ValueError(f"Unknown English label: {class_labels}")
+        class_label_ids = [label2id[class_labels]]
+    elif class_labels and isinstance(class_labels[0], str):
+        if not label2id:
+            raise ValueError("No English labels loaded. Provide `id2label` in the pipeline config.")
+        missing = [item for item in class_labels if item not in label2id]
+        if missing:
+            raise ValueError(f"Unknown English label(s): {missing}")
+        class_label_ids = [label2id[item] for item in class_labels]
+    else:
+        class_label_ids = list(class_labels)
+    return torch.tensor(class_label_ids, device=device, dtype=torch.long).reshape(-1)
+
+
+class GATPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for one-step class-conditional image generation with Generative Adversarial Transformers (GAT).
+    """
+
+    model_cpu_offload_seq = "generator->vae"
+
+    def __init__(
+        self,
+        generator,
+        vae: AutoencoderKL,
+        truncation_psi: float = 0.3,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        self.register_modules(generator=generator, vae=vae)
+        self.register_to_config(truncation_psi=truncation_psi)
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = _normalize_id2label(id2label)
+        self.labels = _build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @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 = _read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = _build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    def _default_image_size(self) -> int:
+        return int(self.generator.config.input_size) * self.vae_scale_factor
+
+    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]]] = None,
+        latents: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        if latents is not None:
+            noise = latents.to(device=device, dtype=dtype)
+        else:
+            latent_height = height // self.vae_scale_factor
+            latent_width = width // self.vae_scale_factor
+            in_channels = int(getattr(self.generator, "in_channels", 4))
+            noise = randn_tensor(
+                (batch_size, in_channels, latent_height, latent_width),
+                generator=generator,
+                device=device,
+                dtype=dtype,
+            )
+        latent_size = int(getattr(self.generator, "latent_size", 64))
+        z = randn_tensor(
+            (batch_size, latent_size),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+        return noise, z, noise
+
+    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)
+
+    @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,
+        truncation_psi: Optional[float] = None,
+        guidance_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)
+        truncation_psi = self.config.truncation_psi if truncation_psi is None else truncation_psi
+
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+
+        device = getattr(self, "_execution_device", None) or next(self.generator.parameters()).device
+        dtype = next(self.generator.parameters()).dtype
+        class_labels_tensor = _normalize_class_labels(
+            class_labels,
+            device=device,
+            label2id=self.labels,
+        )
+        batch_size = class_labels_tensor.shape[0]
+
+        x, z, latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+        )
+
+        output = self.generator(
+            x=x,
+            y=class_labels_tensor,
+            z=z,
+            guidance_scale=guidance_scale,
+            truncation_psi=truncation_psi,
+            return_dict=True,
+        ).sample
+
+        if output_type == "latent":
+            result = output
+        else:
+            result = self.decode_latents(output, output_type=output_type)
+
+        if not return_dict:
+            return (result,)
+        return ImagePipelineOutput(images=result)

GAT-XL-2-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.38.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "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
+}

GAT-XL-2-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+library_name: diffusers
+pipeline_tag: image-to-image
+tags:
+- diffusers
+- gat
+- gan
+- class-conditional
+- imagenet
+inference: true
+widget:
+- output:
+    url: GAT-XL-2-256/demo.png
+language:
+- en
+---
+
+# BiliSakura/GAT-diffusers
+
+Self-contained [Generative Adversarial Transformers (GAT)](https://arxiv.org/abs/2509.24935) checkpoints for Hugging Face diffusers.
+
+Converted from the official GAT XL-2 checkpoint using `libs/GAT-diffusers/scripts/convert_gat_checkpoint.py`.
+
+GAT performs one-step class-conditional image generation in Stable Diffusion VAE latent space (`sd-vae-ft-ema`).
+
+## Demo
+
+`GAT-XL-2-256` — class **207** (*golden retriever*), seed **0**, `truncation_psi=0.3`:
+
+<p align="center">
+  <img src="GAT-XL-2-256/demo.png" alt="GAT-XL-2-256 demo (class 207, seed 0)" width="256"/>
+</p>
+
+## Variants
+
+| Model | Resolution | Params | Checkpoint |
+| --- | --- | --- | --- |
+| GAT-XL/2 | 256×256 | 675M | `GAT-XL-2-256/` |
+
+## Usage
+
+```python
+from pathlib import Path
+import torch
+from diffusers import DiffusionPipeline
+
+model_dir = Path("./GAT-XL-2-256").resolve()
+pipe = DiffusionPipeline.from_pretrained(
+    str(model_dir),
+    custom_pipeline=str(model_dir / "pipeline.py"),
+    trust_remote_code=True,
+    torch_dtype=torch.float32,
+    local_files_only=True,
+).to("cuda")
+
+image = pipe(
+    class_labels="golden retriever",
+    truncation_psi=0.3,
+    generator=torch.Generator("cuda").manual_seed(0),
+).images[0]
+```
+
+## Conversion
+
+```bash
+conda activate rsgen
+python libs/GAT-diffusers/scripts/convert_gat_checkpoint.py \
+  --ckpt models/BiliSakura/GAT-diffusers/gat-xl-2-256.pt \
+  --output-dir models/BiliSakura/GAT-diffusers/GAT-XL-2-256 \
+  --resolution 256
+```