apple/FastFrames-L
text-to-video model by apple
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://apple-aiml-research.github.io/ml-fastframes/) [](https://arxiv.org/abs/2611.23226) [](https://huggingface.co/apple/FastFrames-S) [](https://huggingface.co/apple/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. [](assets/fastframesdemo.mp4) Linux x86-64 with an NVIDIA GPU and a CUDA 12.8-compatible driver. From the repository root: Download FastFrames and third-party weights using the checkpoint guide. Example component timings for FastFrames-S, 1 GPU, 480p, with a full KV cache. See the profiling guide for details and baselines. Complete the demo setup, then launch one of: and open http://localhost:8000. 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): See the generation guide for details. Follow the…
Read the full model card ↗ · Preview checked 2026-11-18T07:00:28.915Z
Inside the original model card — Document outline
- FastFrames: Video Generation at Interactive Latency
- Installation
- Latency Profiling
- Interactive Demo with LingBot
- T2V Generation
- VBench Evaluation
- Training
- Causal Forcing++ -> FastFrames-S
- Wan2.1-14B -> FastFrames-L
- Citation
- License and Acknowledgments
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apple-amlr. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
apple/FastFrames-L is a text-to-video model repository published by apple on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 96
- Hugging Face trending score
- 96
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apple-amlr
- Access
- Not gated by Hugging Face
- Created
- 2026-11-16T17:21:04.000Z
- Last modified
- 2026-11-18T05:29:30.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Wan-AI/Wan2.1-T2V-14B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-18T06:59:26.317Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-T2V-A14B-GGUF
QuantStack/Wan2.2-TI2V-5B-GGUF