OOTDiffusion
Open-source high-resolution virtual try-on model — half-body and full-body support
An open-source high-resolution virtual try-on model supporting half-body and full-body.
AI video generation, digital humans, and video restoration.
Key features
- Outfitting fusion latent diffusion for controllable virtual try-on
- Half-body VITON-HD and full-body DressCode models
- ONNX support for human parsing
- Simple CLI inference with scale and sample controls
Good for
- Virtual try-on from model and garment images
- Fashion e-commerce try-on features
Stack & tags
PythonPyTorchvirtual-try-onfashiondiffusionopen-weightsimage-generationonnxe-commerce
Quick start
python run_ootd.py --model_path <model-image-path> --cloth_path <cloth-image-path> --scale 2.0 --sample 4From the project README on GitHub.
Similar open-source projects
Hyperframes
★ 55,468Write HTML. Render video. Built for agents — HeyGen's open-source video framework
Hypit
★ 18,649Clone any viral video with AI agents — swap the face, the words, the B-roll, ship 100 variants