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.

Date Created 2024-06-23 (8 months ago)

Commits 71 (last one 6 days ago)

Stargazers 247 (6 this week)

Watchers 6 (0 this week)

Forks 15

License unknown

Ranking

RepositoryStats indexes 628,089 repositories, of these mihirp1998/VADER is ranked #160,942 (74th percentile) for total stargazers, and #288,687 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #28,773/127,953.

mihirp1998/VADER is also tagged with popular topics, for these it's ranked: reinforcement-learning (#481/1432)

Other Information

mihirp1998/VADER has Github issues enabled, there are 10 open issues and 8 closed issues.

There have been 3 releases, the latest one was published on 2024-07-12 (8 months ago) with the name VADER V1.0.

Homepage URL: https://vader-vid.github.io/

All Topics

rl rlhf vader alignment diffusion video-diffusion reinforcement-learning video-diffusion-alignment reinforcement-learning-human-feedback

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

71 commits on the default branch (master) since jan '22

Yearly Commits

Commits to the default branch (master) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2025-03-18 @ 06:46am, id: 819132711 / R_kgDOMNL5Jw