Ross ROSS = Recommend OSS · open-source software intelligence for agents

lllyasviel/FramePack

Lets make video diffusion practical! observed · 2026-08-28

github.com/lllyasviel/FramePack · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

31/100

  • Activity 47
  • Release rhythm 8
  • Longevity 36
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 508
  • days_rel: 502
  • days_push: 322
  • n_releases_24m: 1

Full methodology

Adoption not part of the score

17229 stars · 1737 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

application · maturity active

video-processing machine-learning deep-learning llm-inference gui deep-learning artificial-intelligence media windows python video-diffusion text-to-video image-to-video next-frame-prediction generative-ai low-vram video linux gpu desktop

1 source

Member repositories

RepositoryRoleHealth v2
lllyasviel/FramePackmain31

For agents

markdown · JSON · MCP: product_card(name="lllyasviel/FramePack")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem