CatVTON is a compact AI virtual clothing change model, ideal for every fashion enthusiast. CatVTON features a lightweight network with a total of 899.06M parameters, requiring only 49.57M trainable parameters during training. Moreover, it uses less than 8G of VRAM for inference and supports high-resolution 1024x768 images, making it perfect for personal computer use.
Product Entry: https://top.aibase.com/tool/catvton
Key features of the product can be summarized as follows:
1) Lightweight network (total of 899.06M parameters)
2) Efficient parameter training (49.57M parameters trainable)
3) Simplified inference (<8G VRAM at 1024x768 resolution)
The development team of CatVTON recently released the latest code and deployment process on GitHub, including how to quickly deploy CatVTON on ComfyUI. With just a few simple steps, you can experience the latest virtual makeup technology at home.
Installation steps:
First, you need to set up the environment according to the installation guide, then download the ComfyUI-CatVTON files and unzip them into the custom_nodes folder of the ComfyUI project. After completing these steps, start ComfyUI, and you can enjoy the fun of fashion matching.
Of course, if you prefer using the Gradio application, just run a single command, and the system will automatically download the necessary checkpoints from HuggingFace, saving time and effort. Whether you want to perform inference on DressCode or VITON-HD datasets, CatVTON can easily meet your needs, with simple inference commands. Just enter the corresponding instructions in the command line, and you'll see your desired effects in minutes.
Additionally, CatVTON supports multiple precision options to ensure the best experience under different hardware conditions. This model uses image inpainting technology based on Stable Diffusion v1.5, combined with SCHP and DensePose, to automatically generate masks, helping you better apply makeup virtually.
Key Points:
🐈 CatVTON is a lightweight virtual makeup model with 899.06M parameters and low VRAM requirements.
💻 Easily deployable on ComfyUI and Gradio applications, making user operations more convenient.
👗 Capable of inference on VITON-HD and DressCode datasets, offering multiple precision options to suit various hardware conditions.