import model files

README.md

@@ -1,3 +1,4 @@
 ---
 license: mit
 ---
+# Ras-Diff Corridor

controlnet/config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.35.1",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02bcb30b00a9fe83dd4c2c390bf181ab7c7089af011d54dcedcc8394fe28f90f
+size 1445157120

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

logs/controlnet-training/20251129_142148.log

@@ -0,0 +1,99 @@
+11/29/2025 14:21:48 - INFO - __main__ - Distributed environment: DistributedType.NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cuda
+
+Mixed precision type: fp16
+
+11/29/2025 14:21:48 - INFO - __main__ - Starting script: train_controlnet.py
+11/29/2025 14:21:50 - INFO - __main__ - Initializing controlnet weights from unet
+11/29/2025 14:21:52 - INFO - __main__ - Training Arguments: 
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+ controlnet_model_name_or_path: None
+ revision: None
+ variant: None
+ trust_remote_code: False
+ dataset_name_or_path: /home/23132798r/workspace/tmp-smoke/data/controlnet
+ dataset_config_name: None
+ image_column: image
+ conditioning_image_column: conditioning_image
+ caption_column: text
+ resolution: 512
+ center_crop: False
+ random_flip: False
+ validation_ids: [1500, 5500, 8500]
+ validation_steps: 10000
+ output_dir: ./output-controlnet
+ cache_dir: None
+ logging_dir: logs
+ tracker_project_name: controlnet-training
+ checkpointing_steps: None
+ checkpoints_total_limit: None
+ resume_from_checkpoint: None
+ report_to: tensorboard
+ seed: 42
+ train_batch_size: 16
+ num_train_epochs: 3
+ max_train_steps: None
+ gradient_accumulation_steps: 1
+ gradient_checkpointing: False
+ dataloader_num_workers: 8
+ noise_offset: 0.1
+ prediction_type: None
+ adam_beta1: 0.9
+ adam_beta2: 0.999
+ adam_weight_decay: 0.01
+ adam_epsilon: 1e-08
+ max_grad_norm: 1.0
+ learning_rate: 1e-05
+ scale_lr: False
+ lr_scheduler: constant
+ lr_warmup_steps: 0
+ mixed_precision: fp16
+ use_8bit_adam: False
+ allow_tf32: False
+ enable_xformers_memory_efficient_attention: False
+ local_rank: -1 
+
+11/29/2025 14:21:52 - INFO - __main__ - ControlNet Model Config: 
+ FrozenDict({'in_channels': 4, 'conditioning_channels': 3, 'flip_sin_to_cos': True, 'freq_shift': 0, 'down_block_types': ['CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D'], 'mid_block_type': 'UNetMidBlock2DCrossAttn', 'only_cross_attention': False, 'block_out_channels': [320, 640, 1280, 1280], 'layers_per_block': 2, 'downsample_padding': 1, 'mid_block_scale_factor': 1, 'act_fn': 'silu', 'norm_num_groups': 32, 'norm_eps': 1e-05, 'cross_attention_dim': 768, 'transformer_layers_per_block': 1, 'encoder_hid_dim': None, 'encoder_hid_dim_type': None, 'attention_head_dim': 8, 'num_attention_heads': None, 'use_linear_projection': False, 'class_embed_type': None, 'addition_embed_type': None, 'addition_time_embed_dim': None, 'num_class_embeds': None, 'upcast_attention': False, 'resnet_time_scale_shift': 'default', 'projection_class_embeddings_input_dim': None, 'controlnet_conditioning_channel_order': 'rgb', 'conditioning_embedding_out_channels': (16, 32, 96, 256), 'global_pool_conditions': False, 'addition_embed_type_num_heads': 64, '_use_default_values': ['global_pool_conditions', 'addition_embed_type_num_heads']})
+11/29/2025 14:21:54 - INFO - __main__ - ============ Training Begins ============
+11/29/2025 14:21:54 - INFO - __main__ -   Num Epochs = 3
+11/29/2025 14:21:54 - INFO - __main__ -   Instantaneous batch size per device = 16
+11/29/2025 14:21:54 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 16
+11/29/2025 14:21:54 - INFO - __main__ -   Gradient Accumulation steps = 1
+11/29/2025 14:21:54 - INFO - __main__ -   Total optimization steps = 45000
+11/29/2025 16:56:53 - INFO - __main__ - Running validation... 
+11/29/2025 18:15:04 - INFO - accelerate.accelerator - Saving current state to output-controlnet/checkpoint-15000
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Optimizer state saved in output-controlnet/checkpoint-15000/optimizer.bin
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Scheduler state saved in output-controlnet/checkpoint-15000/scheduler.bin
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in output-controlnet/checkpoint-15000/sampler.bin
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in output-controlnet/checkpoint-15000/sampler_1.bin
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Gradient scaler state saved in output-controlnet/checkpoint-15000/scaler.pt
+11/29/2025 18:15:11 - INFO - accelerate.checkpointing - Random states saved in output-controlnet/checkpoint-15000/random_states_0.pkl
+11/29/2025 18:15:11 - INFO - __main__ - Saved state to output-controlnet/checkpoint-15000
+11/29/2025 18:15:12 - INFO - __main__ - Epoch   0 | Global Step 15000
+11/29/2025 19:32:33 - INFO - __main__ - Running validation... 
+11/29/2025 22:08:22 - INFO - accelerate.accelerator - Saving current state to output-controlnet/checkpoint-30000
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Optimizer state saved in output-controlnet/checkpoint-30000/optimizer.bin
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Scheduler state saved in output-controlnet/checkpoint-30000/scheduler.bin
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in output-controlnet/checkpoint-30000/sampler.bin
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in output-controlnet/checkpoint-30000/sampler_1.bin
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Gradient scaler state saved in output-controlnet/checkpoint-30000/scaler.pt
+11/29/2025 22:08:29 - INFO - accelerate.checkpointing - Random states saved in output-controlnet/checkpoint-30000/random_states_0.pkl
+11/29/2025 22:08:29 - INFO - __main__ - Saved state to output-controlnet/checkpoint-30000
+11/29/2025 22:08:29 - INFO - __main__ - Running validation... 
+11/29/2025 22:08:32 - INFO - __main__ - Epoch   1 | Global Step 30000
+11/30/2025 00:43:43 - INFO - __main__ - Running validation... 
+11/30/2025 02:01:21 - INFO - accelerate.accelerator - Saving current state to output-controlnet/checkpoint-45000
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Optimizer state saved in output-controlnet/checkpoint-45000/optimizer.bin
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Scheduler state saved in output-controlnet/checkpoint-45000/scheduler.bin
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in output-controlnet/checkpoint-45000/sampler.bin
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in output-controlnet/checkpoint-45000/sampler_1.bin
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Gradient scaler state saved in output-controlnet/checkpoint-45000/scaler.pt
+11/30/2025 02:01:28 - INFO - accelerate.checkpointing - Random states saved in output-controlnet/checkpoint-45000/random_states_0.pkl
+11/30/2025 02:01:28 - INFO - __main__ - Saved state to output-controlnet/checkpoint-45000
+11/30/2025 02:01:28 - INFO - __main__ - Epoch   2 | Global Step 45000
+11/30/2025 02:01:34 - INFO - __main__ - Running validation... 
+11/30/2025 02:01:37 - INFO - __main__ - Finished!

logs/controlnet-training/events.out.tfevents.1764397314.23132798r-i456aaf7f00.25324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a3cfc43e080794251dc3e72cb5ac652eabad8bbbc85a42f6152b8ec1e7ee4a
+size 2956651

model_index.json

@@ -0,0 +1,42 @@
+{
+  "_class_name": "StableDiffusionControlNetPipeline",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "controlnet": [
+    "diffusers",
+    "ControlNetModel"
+  ],
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.35.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "transformers_version": "4.56.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>",
+  "variant": null
+}

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
+size 1719125304

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "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": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342