The editor of Downcodes brings you a lightweight AI virtual clothes-changing model - CatVTON! It has 899.06M parameters, training only requires 49.57M trainable parameters, consumes less than 8G of video memory during inference, supports 1024x768 high resolution, and is perfectly suitable for personal computers. CatVTON supports ComfyUI and Gradio application deployment, is easy to operate, can perform inference on VITON-HD and DressCode data sets, and provides a variety of accuracy options to meet the use needs under different hardware conditions. What are you waiting for? Come and experience the fun of fashion matching!
CatVTON is a small AI virtual clothing changing model suitable for every fashion lover. CatVTON is characterized by a lightweight network with a total of 899.06M parameters, and only 49.57M trainable parameters are required for training. Moreover, when performing inference, it uses less than 8G of video memory and supports 1024x768 high resolution, which is very suitable for personal computer operation.
Product entrance: https://top.aibase.com/tool/catvton
Product features can be summarized as follows:
1) Lightweight network (899.06M parameters in total)
2) Efficient parameter training (49.57M parameters can be trained)
3) Simplified reasoning (<8G VRAM resolution is 1024X768)
CatVTON's development team 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 try-on technology at home.
Installation steps:
First, you need to set up the environment according to the installation guide, then download the ComfyUI-CatVTON file and extract it to 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 to use the Gradio application, you only need to run a command and the system will automatically download the required checkpoints from HuggingFace, saving time and effort. Whether you want to perform inference on DressCode or VITON-HD data sets, CatVTON can easily meet your needs, and the related inference commands are also very simple. Just enter the corresponding instructions in the command line and you will see the effect you like in a few minutes.
In addition, CatVTON also supports multiple accuracy options to ensure users get the best experience under different hardware conditions. This model uses image restoration technology based on Stable Diffusion v1.5, which combines SCHP and DensePose to automatically generate masks to help you better test makeup.
Highlight:
? CatVTON is a lightweight virtual makeup try-on model with 899.06M parameters and low video memory requirements.
? Supports easy deployment on ComfyUI and Gradio applications, making user operations more convenient.
? Can perform inference on VITON-HD and DressCode data sets, providing multiple accuracy options to adapt to various hardware conditions.
All in all, CatVTON provides fashion lovers with a convenient virtual fitting experience thanks to its lightweight, high efficiency and ease of use. Hurry up and give it a try!