VADER
PublicVideo 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.
alignmentdiffusionreinforcement-learningreinforcement-learning-human-feedbackrlrlhfvadervideo-diffusionvideo-diffusion-alignment
Creat：2024-06-24T05:44:57
Update：2025-03-22T22:36:25
https://vader-vid.github.io/
9
Stars
-292
Stars Increase