# hao-ai-lab/FastVideo

> A framework for accelerated video generation: post-training (distillation, LoRA, sparse attention) and fast inference of diffusion video models on GPU and Apple Silicon.

- Magnitude: 1.5 out of 10 — Steady
- Stars: 4,514 total · +3 stars on 2026-09-28 (UTC), ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2024-10-24 · Last push: 2026-09-27
- GitHub: https://github.com/hao-ai-lab/FastVideo · Homepage: https://hao-ai-lab.github.io/FastVideo · Page: https://gitnova.dev/en/r/hao-ai-lab/FastVideo

## Useful for

- Run DMD2 distillation on an open video model to speed up denoising
- Generate a short video on a single GPU via CLI or Python API
- Finetune a video diffusion model on custom data with LoRA

## Why it’s here

- 3 stars so far today, about 7 expected by the end of the day.
- Recent forks include notable developers: @magicbear (217 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 476
- Issues and pull requests: 1,887
- Watchers: 38
- Average over the last week: 4 per day
- Usual pace: 13 per day
- Latest release: v0.2.0 (2026-06-04)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 12 days

09-17 2.3, 09-18 2.0, 09-19 1.4, 09-20 1.2, 09-21 1.7, 09-22 1.7, 09-23 0.9, 09-24 1.2, 09-25 1.2, 09-26 1.0, 09-27 1.3, 09-28 1.5

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-28 10:29 UTC, updated every 30 minutes.