FastFrames
Type: RepoCategory: Generation
FastFrames is an open-source repo in our Generation category. Apple ML Research open-weight autoregressive two-step video diffusion models, released Nov 2026: FastFrames-S (1.3B) and FastFrames-L (14B, trained from Wan2.1-T2V-14B) generate 832×480 video at interactive latency (per Apple, ~36 ms/frame on one B200 for S), plus a 16× faster LingBot 1.3B build for live camera control. Linux + NVIDIA/CUDA 12.8; research-only license (no commercial use).
Where it fits: Open-weight video & audio models.
Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.
Lab posts that cover FastFrames
Related Lab posts
- Three open-source video tools picking up steam: Mago Studio, Rigby2D and a MiniMax H3 'short-drama workbench' for ComfyUI
- #OpenSourceHiggsfield winners: Panorama Stickers, Blocksfield, Imagination Studio and Paint a Plate, plus 10 open builds worth a look
- Freefield: an open-weights Higgsfield-style studio on ComfyUI (120 apps, Modal or your GPU)
- MoneyPrinterTurbo is trending again: topic in, finished short out
- #OpenSourceHiggsfield closes: five last-hour ComfyUI builds
Similar skills & repos
- Mago Studio · Repo, Generation
- HyperFlow H3 Flash · Repo, Generation
- Freefield · Repo, Generation
- Comfy Previs · Repo, Generation
- IV Studio · Repo, Generation
- Chimera · Repo, Generation