Upload folder using huggingface_hub

DressCode/checkpoint-32000/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

DressCode/checkpoint-32000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-inpainting",
+  "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": 9,
+  "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
+}

DressCode/checkpoint-32000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd294e84218ba7d793bf7b1cf7a9ff8517454abf3b9c1f98d79f46db2e085d4
+size 3438225152

README.md

@@ -1,3 +1,75 @@
----
-license: creativeml-openrail-m
----
+---
+license: creativeml-openrail-m
+tags:
+  - virtual-try-on
+  - diffusers
+  - stable-diffusion
+  - image-to-image
+datasets:
+  - VITON-HD
+  - DressCode
+base_model: runwayml/stable-diffusion-inpainting
+pipeline_tag: image-to-image
+---
+
+# Re-CatVTON
+
+Official model weights for **Re-CatVTON: Revisiting Concatenation-Based Virtual Try-On**.
+
+📄 **Paper**: [Re-CatVTON](https://arxiv.org/abs/2511.18775)  
+💻 **Code**: [GitHub](https://github.com/Levinna/Re-CatVTON)
+
+## Available Checkpoints
+
+| Dataset | Subfolder | Resolution |
+|---------|-----------|------------|
+| VITON-HD | `VITON-HD/checkpoint-16000/unet` | 512×384 |
+| DressCode | `DressCode/checkpoint-32000/unet` | 512×384 |
+
+## Usage
+```python
+import torch
+from diffusers import AutoencoderKL, UNet2DConditionModel, DDPMScheduler
+from model.pipeline import RECATVTONPipeline
+from model.attn_processor import SkipAttnProcessor
+from model.utils import init_adapter
+
+device = "cuda"
+dtype = torch.bfloat16
+
+# Load components
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse").to(device, dtype)
+
+# Choose one:
+unet = UNet2DConditionModel.from_pretrained(
+    "levinna/Re-CatVTON", 
+    subfolder="VITON-HD/checkpoint-16000/unet"  # or "DressCode/checkpoint-32000/unet"
+).to(device, dtype)
+
+scheduler = DDPMScheduler.from_pretrained(
+    "stable-diffusion-v1-5/stable-diffusion-inpainting", # or can use Re-CatVTON scheduler config
+    subfolder="scheduler"
+)
+
+# Initialize attention processors (disable cross-attention)
+init_adapter(unet, cross_attn_cls=SkipAttnProcessor)
+
+# Create pipeline
+pipeline = RECATVTONPipeline(vae=vae, unet=unet, scheduler=scheduler)
+```
+You can check more detailed instruction on Official [GitHub](https://github.com/Levinna/Re-CatVTON)
+
+## License
+
+- **Model Weights**: [CreativeML OpenRAIL-M](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
+- **Code**: [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+
+## Citation
+```bibtex
+@article{na2025rethinking,
+  title={Rethinking Garment Conditioning in Diffusion-based Virtual Try-On},
+  author={Na, Kihyun and Choi, Jinyoung and Kim, Injung},
+  journal={arXiv preprint arXiv:2511.18775},
+  year={2025}
+}
+```

VITON-HD/checkpoint-16000/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

VITON-HD/checkpoint-16000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.1",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-inpainting",
+  "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": 9,
+  "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
+}

VITON-HD/checkpoint-16000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce41428749aad3fdb7e7bd38bbcd374e80967f6b41144a726a488f897afb2e3
+size 3438225152