← authors · overview

• Towards Training-Free Scene Text Editing
  2026
• Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation
  2025
• Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
  2025
• VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning
  2025
• Phased One-Step Adversarial Equilibrium for Video Diffusion Models
  2025
• MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation
  2025
• MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation
  2025
• Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance
  2025
• ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing
  2023
• UGC: Unified GAN Compression for Efficient Image-to-Image Translation
  2023
• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
  2023
• MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
  2023
• DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
  2024
• PuLID: Pure and Lightning ID Customization via Contrastive Alignment
  2024