Skip to content

Awesome-Video-Diffusion vs VBench

Two Datasets & papers projects side by side: what each one is for, what it runs on, and how active it is right now.
In one line
Video diffusion papers and projects, sorted into labeled sections
Scores video generation models on quality, faithfulness and safety
Best for
Research teams who want one map of video diffusion work.
Model-selection teams who need to compare video models on named dimensions.
GitHub stars
5.8k GitHub stars
1.8k GitHub stars
Stars, last 30 days
+2
+2
Last push
10 days ago
1 month ago
Latest release
No releases
v0.1.4, Sep 3, 2024
Forks
375 forks
135 forks
License
No licenseNo license: you can look at the code, but you can't reuse it without asking the author.
Apache-2.0Apache-2.0: you can use and change this code, even in paid products. Just keep the license file.
Models
  • Wan 2.1
  • HunyuanVideo
  • LTX-Video
  • Mochi 1
  • Stable Video Diffusion
  • Open-Sora
  • SkyReels-V2
  • Cosmos
  • Veo 2
  • Kling
  • Gen-3
  • Kling
  • Pika
  • CogVideoX
Languages
English README; UI in English
English README; UI in English
Features
  • Groups links by task, from generation to restoration and 3D
  • Lists benchmarks and metrics for judging video models
  • Covers character and motion customization, plus long video
  • Tracks talking heads, audio synthesis and virtual try-on
  • Also lists commercial video products and game generation
  • Scores text-to-video models on quality, faithfulness and safety
  • Adds image-to-video scoring with an adaptive image suite
  • Handles long videos, like Sora-style clips
  • Checks fairness, bias, culture and safety in outputs
  • VBench-2.0 adds 18 fine-grained dimensions in five categories
  • Ships prompt suites, sample videos and a human anomaly detector
Setup
4 steps
5 steps

Which one to pick

Pick Awesome-Video-Diffusion if…

Research teams who want one map of video diffusion work.

Pick VBench if…

Model-selection teams who need to compare video models on named dimensions.

Stars and activity come from GitHub and update daily. We last checked the descriptions on Oct 1, 2026.