# hao-ai-lab/FastVideo

A unified inference and post-training framework for accelerated video generation.

Repository: https://github.com/hao-ai-lab/FastVideo
Canonical: https://ross.abutalabs.com/products/fastvideo
Homepage: https://hao-ai-lab.github.io/FastVideo
Language: Python
License: Apache-2.0
License Family: permissive
Topics: diffusers, diffusion-models, video-generation, distillation, inference, post-training
Last push: 2026-08-26T22:51:57+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 75, longevity 48
- inputs: {"age_days": 679, "days_push": 7, "days_rel": 90, "gap_med": 35.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4076, forks 418 (observed 2026-08-28T04:08:34.308162+00:00)

## What it is
FastVideo is a unified Python framework for post-training and real-time inference of video diffusion models, covering data preprocessing, finetuning (full and LoRA), stepwise/causal distillation, quantization-aware training, and accelerated inference. It supports NVIDIA CUDA GPUs and Apple Silicon via MLX, with both CLI and Python APIs.

## Use cases
- generate videos from text prompts with diffusion models
- distill a video diffusion model to run in few steps
- finetune or LoRA-train a video DiT model on custom data
- run realtime video generation on a single GPU
- quantize a video model with QAT for faster inference
- run video generation locally on Apple Silicon Macs

## When to choose
- you need end-to-end video diffusion training, distillation, and inference in one framework
- you want state-of-the-art speedups like DMD2 distillation, sparse attention, or quantization
- you need distributed training/inference with FSDP2 and sequence parallelism
- you want realtime streaming video generation or editing

## When to avoid
- you only need simple image generation rather than video
- you want a no-code GUI tool rather than Python/CLI workflows
- you lack a supported GPU (CUDA 12.6+ NVIDIA or Apple Silicon M-series)
- you need a lightweight inference-only library without training features

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, video-processing, gpu-computing, cli
- domain: deep-learning, machine-learning, artificial-intelligence, gpu-computing
- platform: python, cli
- tags: diffusion-models, video-generation, distillation, post-training, lora-finetuning, quantization, sparse-attention, realtime-inference, diffusers, apple-silicon, video, linux, macos, gpu

## Member repositories
- hao-ai-lab/FastVideo (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.308162+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:27.562786+00:00, confidence not recorded.
  - readme: https://github.com/hao-ai-lab/FastVideo (fetched 2026-08-28T04:08:34.308162+00:00, sha 9b4bec42d5e4)
  - homepage: https://hao-ai-lab.github.io/FastVideo (fetched 2026-08-29T09:15:27.368688+00:00, sha 111e7ea53265)
  - site_page: https://haoailab.com/FastVideo/getting_started/installation (fetched 2026-08-29T09:15:27.371232+00:00, sha d9c3823c8c60)
  - site_page: https://haoailab.com/FastVideo/getting_started/installation/mps (fetched 2026-08-29T09:15:27.373010+00:00, sha 904833c55770)
  - registry_pypi: https://pypi.org/pypi/fastvideo/json (fetched 2026-08-29T09:15:27.374958+00:00, sha c19922bcf52b)
- Data as of 2026-08-30T08:39:29.467469+00:00.