AlphaUncommon
mihirp1998/VADER
Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.
- Owner
- mihirp1998 (personal account)
- Stars
- Stars: 318
- Forks
- Forks: 15
- Language
- Python
- License
- None
- Created
- 2024
- Topics
- alignmentdiffusionrlhfvideo-diffusionreinforcement-learningrlvaderreinforcement-learning-human-feedbackvideo-diffusion-alignment
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by mihirp1998
All 2 repos by mihirp1998- mihirp1998/AlignPropStars: 330PythonAlpha
Nearby in Python
All Python repos- AMAP-ML/DreamX-CreatorStars: 318PythonAlpha
- Blueforcer/ComfyUI-DLSS5-EnhancerStars: 318PythonAlpha
- danieldeer/seriousdbStars: 318PythonAlpha
- johnpaulett/python-hl7Stars: 318PythonAlpha
- alex/pretendStars: 318PythonAlpha
- trustedsec/ridenumStars: 318PythonAlpha