hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
No releases in the last 90 days; the most recent was 150 days ago, with 112 contributors on GitHub.
Use Cases & Benefits
- Provides a unified framework for accelerated video generation using diffusion models with end-to-end post-training and inference optimizations.
- Delivers state-of-the-art speedups and modular extensibility for video diffusion model training, finetuning, distillation, and inference across diverse hardware.
- Use for accelerating video generation workflows requiring scalable training and fine-tuning of diffusion-based video models on multi-GPU setups.
- Use for implementing post-training optimizations like sparse distillation and sliding tile attention to boost inference speed without retraining.
- Use for research and development of novel video diffusion techniques leveraging modular pipelines and support for advanced sparse attention mechanisms.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
FastVideo is a unified post-training and inference framework for accelerated video generation.
FastVideo features an end-to-end unified pipeline for accelerating diffusion models, starting from data preprocessing to model training, finetuning, distillation, and inference. FastVideo is designed to be modular and extensible, allowing users to easily add new optimizations and techniques. Whether it is training-free optimizations or post-training optimizations, FastVideo has you covered.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+832 stars over 83 days across 12 snapshot days; best day +47 on Aug 29.
Forks
515+116
Open issues
154+23
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| photoprism/photoprism | 40.4K | — | 65 | 1 day ago |
| huggingface/diffusers | 34.8K | — | 65 | 3 days ago |
| onnx/onnx | 21.6K | — | 63 | 31 days ago |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| milesial/Pytorch-UNet | 11.7K | — | 18 | — |
| hao-ai-lab/FastVideo | 4.8K | — | 47 | 150 days ago |
| Category median | 21.6K | — | 63 | — |
Discover Repositories
Search across tracked repositories by name or description