- Status
- Verified
- Base model
- …
- Lineage
- …
- Unchanged from base
- …
- Trending
- #3
- Downloads, 30 days
- 0
- Weights
- 174 GB
- Revision
This repository contains the official implementation of FastFrames: Video Generation at Interactive Latency. We release FastFrames-S (1.3B) and FastFrames-L (14B).
At a glance
- Task
- Text to video
- Input
- text
- Output
- video
- License
- apple-amlr
- Base model
- Fine tuned from Wan-AI/Wan2.1-T2V-14B
- Released
- Nov 2026
- Updated
- Nov 2026
- Likes
- 151
- Downloads, all time
- 0
Run it
Pinned to the indexed revision.
hf download apple/FastFrames-L --revision 18f30cbdd91943baa274e4237dd09b6d19e58ca9Through the hub: the same tools, each file from a source that is up (Hugging Face, ModelScope, IPFS), at this revision. The last line checks every file against the hash the tree names.
export HF_ENDPOINT=https://gethologram.ai
hf download apple/FastFrames-L --quiet && hf cache verify apple/FastFrames-LPapers
- FastFrames: Video Generation at Interactive LatencyGene Chou et al., 2026
Spaces
Used in 2 Spaces.
Read the full model card
FastFrames: Video Generation at Interactive Latency
Project Page arXiv FastFrames-S FastFrames-L
This repository contains the official implementation of FastFrames: Video Generation at Interactive Latency. We release FastFrames-S (1.3B) and FastFrames-L (14B). Both are autoregressive, two-step video diffusion models that generate 480p video at interactive latency. We also release an optimized version of LingBot 1.3B that is 16x faster than the official model and allows fluid camera-conditioned control.
Installation
Linux x86-64 with an NVIDIA GPU and a CUDA 12.8-compatible driver. From the repository root:
uv sync
Download FastFrames and third-party weights using the checkpoint guide.
Latency Profiling
uv run python evaluation/latency/benchmark.py ff-s
uv run python evaluation/latency/benchmark.py ff-l --gpus 8
Example component timings for FastFrames-S, 1 GPU, 480p, with a full KV cache.
| Component | Calls | Latency per call | Total latency |
|---|---|---|---|
| DiT evaluation, t=1000 | 1 | 16.1 ms | 16.1 ms |
| DiT evaluation, t=833 | 1 | 16.2 ms | 16.2 ms |
| KV refinement | 1 | 2.2 ms | 2.2 ms |
| Pixel decoder | 1 | 0.9 ms | 0.9 ms |
| Total | 35.4 ms (paper: 36 ms) |
See the profiling guide for details and baselines.
Interactive Demo with LingBot
Complete the demo setup, then launch one of:
CUDA_VISIBLE_DEVICES=0 uv run --extra lingbot --extra demo python apps/lingbot/demo.py --gpus 1
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 uv run --extra lingbot --extra demo python apps/lingbot/demo.py --gpus 8
and open http://localhost:8000.
T2V Generation
uv run python scripts/generate.py --model ff-s --checkpoint-dir checkpoints \
--prompt "A corgi surfing a wave at sunset" --seed 0 --output outputs/corgi.mp4
Outputs 832 × 480 video, 81 frames at 16 fps. Use --model ff-l for FastFrames-L.
To generate the videos on our project page (20+ videos):
uv run python scripts/generate_project_page.py --model ff-s --output-dir outputs/project_page/ff-s
uv run python scripts/generate_project_page.py --model ff-l --output-dir outputs/project_page/ff-l
See the generation guide for details.
VBench Evaluation
Follow the evaluation guide to reproduce Table 1's Quality / Semantic / Total scores.
Training
Causal Forcing++ -> FastFrames-S
FastFrames-S keeps the two-step frame-wise Causal Forcing++ generator frozen and trains the networks around it.
Wan2.1-14B -> FastFrames-L
We first distill Wan2.1-14B into a two-step causal model following the Causal Forcing++ recipe, then train its pixel decoder and KV refinement network as for FastFrames-S. We release all checkpoints: 1) a causal teacher trained on latents generated by Wan2.1-14B; 2) the consistency-distilled model; 3) the DMD-distilled model; 4) the final generator, pixel decoder and KV refinement network.
Citation
If you find this work useful in your research, please cite:
@article{chou2026fastframes,
title = {FastFrames: Video Generation at Interactive Latency},
author = {Chou, Gene and Yang, Guandao and Luan, Fujun and Mescheder, Lars and
Dong, Wei and Richter, Stephan R. and Koltun, Vladlen},
journal = {arXiv preprint arXiv:2611.23226},
year = {2026}
}
License and Acknowledgments
LingBot-World v2 code and weights follow their upstream CC BY-NC-SA 4.0 license. All other FastFrames code is licensed under the Apple Sample Code License. Also see ACKNOWLEDGEMENTS for third-party code.
We thank the authors of Wan2.1, Self-Forcing, and Causal Forcing++ for releasing their code, on which the FastFrames code and models build.
Derived on Nov 18, 2026 from Hugging Face at revision 18f30cbd, README.md .
20 files, 174 GB. Every download is checked against its address.
