#143 · Primary category: Image Generation

ComfyUI-IDM-VTON

comfy comfyui comfyui-nodes inpainting stable-diffusion virtual-try-on virtual-tryon

ComfyUI adaptation of IDM-VTON for virtual try-on.

Project last updated:08/20/24

GitHub Stars

588

Forks

72

Contributors

7

License

GPL-3.0

Why we included this project

ComfyUI users who want to preview how a garment fits on a real person can run IDM-VTON through this node pack without leaving their existing graph. It takes a clothing image and a photo of a person and returns a try-on result where the fabric follows the body rather than being pasted on top. The two fiddly prerequisites are handled by companion nodes: Segment Anything generates the garment mask and ControlNet Auxiliary Preprocessors estimate DensePose, so you wire those in instead of reimplementing them. Teams building e-commerce fitting tools and fashion editors can use it as a base for try-on work. Two caveats matter before you commit: it needs at least 16GB of VRAM, and the license inherited from the original model is non-commercial.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category