MagicTryOn
Zhejiang University + vivo video virtual try-on — change outfits on people in videos
Zhejiang University + vivo video virtual try-on: change the outfits of people in videos.
AI video generation, digital humans, and video restoration.
Key features
- Video virtual try-on with Wan2.1 diffusion Transformer backbone
- Coarse-to-fine garment preservation with mask-aware loss
- Image try-on, video try-on, and customizable try-on modes
- 1.3B and Turbo variants released
- Full self-attention for spatiotemporal consistency
Good for
- Virtual try-on for fashion e-commerce
- Garment-preserving video try-on demos
Stack & tags
Pythonvirtual-try-onvideodiffusionopen-weightsfashiongarment-preservationwan2.1
Quick start
CUDA_VISIBLE_DEVICES=0 python inference/video_tryon/predict_video_tryon_up.pyFrom 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