Skip to content
ModelListedExternal
Browse files

Cat Tryoff Flux

CAT-Tryoff-Flux is an advanced tryoff model. It used the same method of (CATVTON-FLUX)[ This model can extract and reconstruct the front view of clothing items from images of people wearing them.

KindModelBase modelblack-forest-labs/FLUX.1-Fill-devVersionDiffusion pytorch model 00001 of 00003

Model source

Kind
Model
File size
3.57–9.30 GB
Base model
black-forest-labs/FLUX.1-Fill-dev
Version
vDiffusion pytorch model 00001 of 00003
Updated
Oct 15, 2026
Source
Hugging Face

Source description

Model Card for CAT-Tryoff-Flux

CAT-Tryoff-Flux is an advanced tryoff model. It used the same method of (CATVTON-FLUX)[https://huggingface.co/xiaozaa/catvton-flux-alpha]. This model can extract and reconstruct the front view of clothing items from images of people wearing them.

Model Details

Model Description

Model Sources [optional]

Uses

The model is designed for virtual try-off applications, allowing users to visualize how different garments would look on a person. It can be used directly through command-line interface with the following parameters:

Input person image Person mask Garment image Random seed (optional)

How to Get Started with the Model

transformer = FluxTransformer2DModel.from_pretrained(
    "xiaozaa/cat-tryoff-flux", 
    torch_dtype=torch.bfloat16
)
pipe = FluxFillPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    transformer=transformer,
    torch_dtype=torch.bfloat16
).to("cuda")


Training Details

Training Data

VITON-HD dataset

Training Procedure

Finetuning Flux1-dev-fill

Evaluation

Summary

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}, 
}
@article{lhhuang2024iclora,
  title={In-Context LoRA for Diffusion Transformers},
  author={Huang, Lianghua and Wang, Wei and Wu, Zhi-Fan and Shi, Yupeng and Dou, Huanzhang and Liang, Chen and Feng, Yutong and Liu, Yu and Zhou, Jingren},
  journal={arXiv preprint arxiv:2410.23775},
  year={2024}
}

Sources

1 source
Hugging FacePrimaryVersion 476deea0f77173fa4644ecf52fdbe28c46945f13
huggingface.co/xiaozaa/cat-tryoff-flux/tree/476deea0f77173fa4644ecf52fdbe28c46945f13

Verified Oct 15

Download files

Model artifacts

3 artifacts

diffusion_pytorch_model-00001-of-00003.safetensors

safetensors · 9.30 GB · SHA-256 5d72bc5d93b9…035d · Hugging Face

Download shard

diffusion_pytorch_model-00002-of-00003.safetensors

safetensors · 9.30 GB · SHA-256 9653e049deda…dfbf · Hugging Face

Download shard

diffusion_pytorch_model-00003-of-00003.safetensors

safetensors · 3.57 GB · SHA-256 32ab2b95c896…bd54 · Hugging Face

Download shard

Source excerpts

2 excerpts

--- library_name: diffusers license: cc-by-nc-2.0 base_model: - black-forest-labs/FLUX.1-Fill-dev pipeline_tag: image-to-image tags: - tryon - vto --- # Model Card for CAT-Tryoff-Flux CAT-Tryoff-Flux is an advanced tryoff model. It used the same method of (CATVTON-FLUX)[https://huggingface.co/xiaozaa/catvton-flux-alpha]. This model can extract and reconstruct the front view of clothing items from images of people wearing them. ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [X/Twitter:Black Magic An](https://x.com/MrsZaaa) ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [github](https://github.com/nftblackmagic/catvton-flux) ## Uses The model is designed for virtual try-off applications, allowing users to visualize how different garments would look on a person. It can be used directly through command-line interface with the following parameters: Input person image Person mask Garment image Random seed (optional) ## How to Get Started with the Model ``` transformer = FluxTransformer2DModel.from_pretrained( "xiaozaa/cat-tryoff-flux", torch_dtype=torch.bfloat16 ) pipe = FluxFillPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", transformer=transformer, torch_dtype=torch.bfloat16 ).to("cuda") ``` ## Training Details ### Training Data VITON-HD dataset ### Training Procedure Finetuning Flux1-dev-fill ## Evaluation #### Summary **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}, } @article{lhhuang2024iclora, title={In-Context LoRA for Diffusion Transformers}, author={Huang, Lianghua and Wang, Wei and Wu, Zhi-Fan and Shi, Yupeng and Dou, Huanzhang and Liang, Chen and Feng, Yutong and Liu, Yu and Zhou, Jingren}, journal={arXiv preprint arxiv:2410.23775}, year={2024} } ```

Source context: 181 downloads · 17 likes · Pipeline image-to-image · Library diffusers · Repo xiaozaa/cat-tryoff-flux