Squashed commit of the following:

commit 711be4b264f23280126a018015425edf410d897d
Author: ZhengChong <[email protected]>
Date: Sat Aug 10 10:24:22 2024 +0000

Update README.md

commit 9927c88b502496a8982561baff755c8c9aafc973
Author: ZhengChong <[email protected]>
Date: Wed Jul 24 08:52:32 2024 +0000

Update README.md

commit 407b9c176177519b9de3811e39a178147ef04710
Author: ZhengChong <[email protected]>
Date: Wed Jul 24 02:26:37 2024 +0000

Update README.md

commit 3ab4d51a08c5da460f9728386de12498def8ca82
Author: ZhengChong <[email protected]>
Date: Mon Jul 22 10:14:16 2024 +0000

Update README.md

commit eb2c1f4eaa24540809868fb7620f1f426c84f850
Author: ZhengChong <[email protected]>
Date: Mon Jul 22 07:45:50 2024 +0000

Update README.md

commit dc4ee0a023d380761a6a2fa7e010d4083bbfdd87
Author: ZhengChong <[email protected]>
Date: Mon Jul 22 07:45:11 2024 +0000

Update README.md

commit a952377d60b2edbf738157b22a5f90d93653c559
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 14:13:36 2024 +0000

Update README.md

commit a9461ab8209633a5a2f49bf45f98c50421ba813d
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 14:11:34 2024 +0000

Update README.md

commit 9baf1221b3b20921401372fe8e79b3e033b4bfc3
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 14:08:38 2024 +0000

Update README.md

commit a2794fce568947daa7c599247156abda373bb985
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 14:07:51 2024 +0000

Update README.md

commit 2c508e565b09c1b6dbee222b9780827c0111fde3
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 11:37:52 2024 +0000

Upload AutoMask related checkpoints

commit bcb9b0fee29627b041943b5c357fa0b5ed3f6be9
Author: ZhengChong <[email protected]>
Date: Sun Jul 21 10:32:27 2024 +0000

Upload ckpts

DensePose/Base-DensePose-RCNN-FPN.yaml

@@ -0,0 +1,48 @@
+VERSION: 2
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 2
+    POOLER_TYPE: "ROIAlign"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+DATASETS:
+  TRAIN: ("densepose_coco_2014_train", "densepose_coco_2014_valminusminival")
+  TEST: ("densepose_coco_2014_minival",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+  WARMUP_FACTOR: 0.1
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

DensePose/densepose_rcnn_R_50_FPN_s1x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

DensePose/model_final_162be9.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a7382001b16e453bad95ca9dbc68ae8f2b839b304cf90eaf5c27fbdb4dae91
+size 255757821

README.md

@@ -1,3 +1,167 @@
----
-license: cc-by-nc-sa-4.0
----
+---
+license: cc-by-nc-sa-4.0
+---
+
+# 🐈 CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
+
+<div style="display: flex; justify-content: center; align-items: center;">
+  <a href="http://arxiv.org/abs/2407.15886" style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/arXiv-2407.15886-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'>
+  </a>
+  <a href='https://huggingface.co/zhengchong/CatVTON' style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/Hugging Face-ckpts-orange?style=flat&logo=HuggingFace&logoColor=orange' alt='huggingface'>
+  </a>
+  <a href="https://github.com/Zheng-Chong/CatVTON" style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/GitHub-Repo-blue?style=flat&logo=GitHub' alt='GitHub'>
+  </a>
+  <a href="http://120.76.142.206:8888" style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/Demo-Gradio-gold?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
+  </a>
+  <a href="https://huggingface.co/spaces/zhengchong/CatVTON" style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/Space-ZeroGPU-orange?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
+  </a>
+  <a href='https://zheng-chong.github.io/CatVTON/' style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/Webpage-Project-silver?style=flat&logo=&logoColor=orange' alt='webpage'>
+  </a>
+  <a href="https://github.com/Zheng-Chong/CatVTON/LICENCE" style="margin: 0 2px;">
+    <img src='https://img.shields.io/badge/License-CC BY--NC--SA--4.0-lightgreen?style=flat&logo=Lisence' alt='License'>
+  </a>
+</div>
+
+
+
+**CatVTON** is a simple and efficient virtual try-on diffusion model with ***1) Lightweight Network (899.06M parameters totally)***, ***2) Parameter-Efficient Training (49.57M parameters trainable)*** and ***3) Simplified Inference (< 8G VRAM for 1024X768 resolution)***.
+
+
+
+## Updates
+- **`2024/08/10`**: Our 🤗 [**HuggingFace Space**](https://huggingface.co/spaces/zhengchong/CatVTON) is available now! Thanks for the grant from [**ZeroGPU**](https://huggingface.co/zero-gpu-explorers)！
+- **`2024/08/09`**: [**Evaluation code**](https://github.com/Zheng-Chong/CatVTON?tab=readme-ov-file#3-calculate-metrics) is provided to calculate metrics 📚.
+- **`2024/07/27`**: We provide code and workflow for deploying CatVTON on [**ComfyUI**](https://github.com/Zheng-Chong/CatVTON?tab=readme-ov-file#comfyui-workflow) 💥.
+- **`2024/07/24`**: Our [**Paper on ArXiv**](http://arxiv.org/abs/2407.15886) is available 🥳!
+- **`2024/07/22`**: Our [**App Code**](https://github.com/Zheng-Chong/CatVTON/blob/main/app.py) is released, deploy and enjoy CatVTON on your mechine 🎉!
+- **`2024/07/21`**: Our [**Inference Code**](https://github.com/Zheng-Chong/CatVTON/blob/main/inference.py) and [**Weights** 🤗](https://huggingface.co/zhengchong/CatVTON) are released.
+- **`2024/07/11`**: Our [**Online Demo**](http://120.76.142.206:8888) is released 😁.
+
+
+
+
+## Installation
+An [Installation Guide](https://github.com/Zheng-Chong/CatVTON/blob/main/INSTALL.md) is provided to help build the conda environment for CatVTON. When deploying the app, you will need Detectron2 & DensePose, which are not required for inference on datasets. Install the packages according to your needs.
+
+## Deployment 
+### ComfyUI Workflow
+We have modified the main code to enable easy deployment of CatVTON on [ComfyUI](https://github.com/comfyanonymous/ComfyUI). Due to the incompatibility of the code structure, we have released this part in the [Releases](https://github.com/Zheng-Chong/CatVTON/releases/tag/ComfyUI), which includes the code placed under `custom_nodes` of ComfyUI and our workflow JSON files.
+
+To deploy CatVTON to your ComfyUI, follow these steps:
+1. Install all the requirements for both CatVTON and ComfyUI, refer to [Installation Guide for CatVTON](https://github.com/Zheng-Chong/CatVTON/blob/main/INSTALL.md) and [Installation Guide for ComfyUI](https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#installing).
+2. Download [`ComfyUI-CatVTON.zip`](https://github.com/Zheng-Chong/CatVTON/releases/download/ComfyUI/ComfyUI-CatVTON.zip) and unzip it in the `custom_nodes` folder under your ComfyUI project (clone from [ComfyUI](https://github.com/comfyanonymous/ComfyUI)).
+3. Run the ComfyUI.
+4. Download [`catvton_workflow.json`](https://github.com/Zheng-Chong/CatVTON/releases/download/ComfyUI/catvton_workflow.json) and drag it into you ComfyUI webpage and enjoy 😆!
+
+> Problems under Windows OS, please refer to [issue#8](https://github.com/Zheng-Chong/CatVTON/issues/8).
+> 
+When you run the CatVTON workflow for the first time, the weight files will be automatically downloaded, usually taking dozens of minutes.
+
+ 
+<!-- <div align="center">
+ <img src="resource/img/comfyui.png" width="100%" height="100%"/>
+</div> -->
+
+### Gradio App
+
+To deploy the Gradio App for CatVTON on your machine, run the following command, and checkpoints will be automatically downloaded from HuggingFace.
+
+```PowerShell
+CUDA_VISIBLE_DEVICES=0 python app.py \
+--output_dir="resource/demo/output" \
+--mixed_precision="bf16" \
+--allow_tf32 
+```
+When using `bf16` precision, generating results with a resolution of `1024x768` only requires about `8G` VRAM.
+
+## Inference
+### 1. Data Preparation
+Before inference, you need to download the [VITON-HD](https://github.com/shadow2496/VITON-HD) or [DressCode](https://github.com/aimagelab/dress-code) dataset.
+Once the datasets are downloaded, the folder structures should look like these:
+```
+├── VITON-HD
+|   ├── test_pairs_unpaired.txt
+│   ├── test
+|   |   ├── image
+│   │   │   ├── [000006_00.jpg | 000008_00.jpg | ...]
+│   │   ├── cloth
+│   │   │   ├── [000006_00.jpg | 000008_00.jpg | ...]
+│   │   ├── agnostic-mask
+│   │   │   ├── [000006_00_mask.png | 000008_00.png | ...]
+...
+```
+For the DressCode dataset, we provide [our preprocessed agnostic masks](https://drive.google.com/drive/folders/1uT88nYQl0n5qHz6zngb9WxGlX4ArAbVX?usp=share_link), download and place in `agnostic_masks` folders under each category.
+```
+├── DressCode
+|   ├── test_pairs_paired.txt
+|   ├── test_pairs_unpaired.txt
+│   ├── [dresses | lower_body | upper_body]
+|   |   ├── test_pairs_paired.txt
+|   |   ├── test_pairs_unpaired.txt
+│   │   ├── images
+│   │   │   ├── [013563_0.jpg | 013563_1.jpg | 013564_0.jpg | 013564_1.jpg | ...]
+│   │   ├── agnostic_masks
+│   │   │   ├── [013563_0.png| 013564_0.png | ...]
+...
+```
+
+### 2. Inference on VTIONHD/DressCode
+To run the inference on the DressCode or VITON-HD dataset, run the following command, checkpoints will be automatically downloaded from HuggingFace.
+
+```PowerShell
+CUDA_VISIBLE_DEVICES=0 python inference.py \
+--dataset [dresscode | vitonhd] \
+--data_root_path <path> \
+--output_dir <path> 
+--dataloader_num_workers 8 \
+--batch_size 8 \
+--seed 555 \
+--mixed_precision [no | fp16 | bf16] \
+--allow_tf32 \
+--repaint \
+--eval_pair  
+```
+### 3. Calculate Metrics
+
+After obtaining the inference results, calculate the metrics using the following command: 
+
+```PowerShell
+CUDA_VISIBLE_DEVICES=0 python eval.py \
+--gt_folder <your_path_to_gt_image_folder> \
+--pred_folder <your_path_to_predicted_image_folder> \
+--paired \
+--batch_size=16 \
+--num_workers=16 
+```
+
+-  `--gt_folder` and `--pred_folder` should be folders that contain **only images**.
+- To evaluate the results in a paired setting, use `--paired`; for an unpaired setting, simply omit it.
+- `--batch_size` and `--num_workers` should be adjusted based on your machine.
+
+
+## Acknowledgement
+Our code is modified based on [Diffusers](https://github.com/huggingface/diffusers). We adopt [Stable Diffusion v1.5 inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) as the base model. We use [SCHP](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing/tree/master) and [DensePose](https://github.com/facebookresearch/DensePose) to automatically generate masks in our [Gradio](https://github.com/gradio-app/gradio) App and [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow. Thanks to all the contributors!
+
+## License
+All the materials, including code, checkpoints, and demo, are made available under the [Creative Commons BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license. You are free to copy, redistribute, remix, transform, and build upon the project for non-commercial purposes, as long as you give appropriate credit and distribute your contributions under the same license.
+
+
+## Citation
+
+```bibtex
+@misc{chong2024catvtonconcatenationneedvirtual,
+ title={CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models}, 
+ author={Zheng Chong and Xiao Dong and Haoxiang Li and Shiyue Zhang and Wenqing Zhang and Xujie Zhang and Hanqing Zhao and Xiaodan Liang},
+ year={2024},
+ eprint={2407.15886},
+ archivePrefix={arXiv},
+ primaryClass={cs.CV},
+ url={https://arxiv.org/abs/2407.15886}, 
+}
+```

SCHP/exp-schp-201908261155-lip.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24fa3254ceeb74c8435458994a64b522fb439a3635b7b86ff470457e0413da00
+size 267449349

SCHP/exp-schp-201908301523-atr.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d7c91ce3b4e7133df56b599fc817b533e3439c5e8d282a59126d2fda339a2a
+size 267445237

dresscode-16k-512/attention/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65a6c64a9bc48e8009a0006d5272b9332c1077c9c2a74302cbac9f256e84cbf
+size 198303368

mix-48k-1024/attention/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fc093f1b6744623079e6f4e7313411f524e388c4b7467df1e0e7f577cba23a
+size 198303368

vitonhd-16k-512/attention/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915df7bf19a33bee36a28d5f9ceaef1e2267c47526f98ca9e4c49e90ae5f0fd0
+size 198303368