█

AI/TLDR

Apple · 2026-11-17 · notable

FastFrames — Apple's video models generate 480p frames in under 50 ms

In short

Apple's FastFrames are 1.3B and 14B autoregressive video diffusion models that reach interactive latency at 480p: 36 ms per frame on one B200 for the small model, 45 ms on an 8x B200 node for the 14B.

Apple · 2026-11-17 · 4 sources checked

Hugging Face model card preview for apple/FastFrames-L

Apple speeds up autoregressive video diffusion to interactive latency by fixing the decoder and KV-cache bottlenecks.

Key specs

Latency (1.3 b, 1x b200)36 ms / frame

What is it?

FastFrames is a pair of text-to-video models from Apple researchers: FastFrames-S (1.3B) and FastFrames-L (14B, fine-tuned from Wan2.1-T2V-14B). Both generate 480p video one chunk at a time fast enough to react to input, and FastFrames-L sits in the Hugging Face trending top 10.

How does it work?

The paper profiled existing streaming video pipelines and found VAE decoding and KV cache updates took over half of end-to-end latency. FastFrames swaps them for a KV cache refinement step and a lightweight pixel decoder, plus systems work that speeds up diffusion sampling. The authors report one generation step falling from 271.8 ms to 35.8 ms.

Why does it matter?

The 1.3B model matches the quality of a model nearly 8x slower, and the project page shows the method speeding up LingBot camera-controlled generation by 16x, so it applies to interactive world models, not only clips. Licensing is restrictive: Apple's research license on the weights, Apple Sample Code License on the code, and CC BY-NC-SA 4.0 for the LingBot parts.

Who is it for?

researchers building real-time video and world models

Try it

https://github.com/apple-aiml-research/ml-fastframes

Sources · 4 outlets

Tags

  • apple
  • fastframes
  • video-generation
  • text-to-video
  • real-time
  • autoregressive-diffusion
  • wan-2-1
  • open-weights
  • world-models

← All releases · Learn AI