# lllyasviel/FramePack

Lets make video diffusion practical!

Repository: https://github.com/lllyasviel/FramePack
Canonical: https://ross.abutalabs.com/products/framepack
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-10-16T01:28:50+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 8, longevity 36
- inputs: {"age_days": 508, "days_push": 322, "days_rel": 502, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17229, forks 1737 (observed 2026-08-28T04:11:17.879030+00:00)

## What it is
FramePack is a next-frame-prediction video diffusion framework and desktop application that generates long videos progressively while compressing input contexts to a constant length. It enables 13B-model video generation on consumer GPUs with as little as 6GB of VRAM.

## Use cases
- generate long videos from a text prompt locally
- image-to-video generation on a low-VRAM laptop GPU
- run 13B video diffusion models on consumer hardware
- progressive anti-drifting video generation
- create 60-second 30fps videos with a desktop app

## When to avoid
- you need an API or hosted web service
- you lack an NVIDIA RTX 30XX/40XX/50XX GPU
- you need macOS support

## Facets
- artifact type: application
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference, gui
- domain: deep-learning, artificial-intelligence, media
- platform: windows, python
- tags: video-diffusion, text-to-video, image-to-video, next-frame-prediction, generative-ai, low-vram, video, linux, gpu, desktop

## Member repositories
- lllyasviel/FramePack (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:17.879030+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 2026-08-29T17:03:27.251648+00:00, confidence not recorded.
  - readme: https://github.com/lllyasviel/FramePack (fetched 2026-08-28T04:11:17.879030+00:00, sha 2053ed330a1d)
- Data as of 2026-08-30T08:39:29.467469+00:00.