FastFrames: Video Generation at Interactive Latency

Gene Chou, Guandao Yang, Fujun Luan, Lars Mescheder, Wei Dong, Stephan Richter, Vladlen Koltun

FastFrames: Video Generation at Interactive Latency: 24 upvotes on Hugging Face Daily Papers, #8 of 39 papers on 2026-11-18. Day-by-day upvote history.

Upvotes over time

It had 22 upvotes by its first day, 24 upvotes by the next day, 24 upvotes by day 3, 24 upvotes by day 7, and has 24 now. It ranked #23 of 146 papers in its week and #124 of 520 in its month. Its code repository has 52 GitHub stars.

Autoregressive video diffusion models generate frames based on new observations and inputs, making them a promising medium for interactive visual experiences. However, existing models are orders of magnitude too slow for fluid interaction. This paper introduces FastFrames, a family of fast autoregressive video diffusion models that achieves interactive latency without compromising quality. We profile the inference pipeline of state-of-the-art models and find that operations often treated as fixed implementation details, such as VAE decoding and KV cache updates, in fact account for over half of end-to-end inference latency. We challenge the assumption that these components are indispensable and replace them with lightweight alternatives. Our 1.3B variant runs at 36 ms per frame, or 28 responses per second (RPS), on a single B200 GPU while matching the generation quality of a state-of-the-art model that is nearly 8x slower. Our 14B variant runs at 45 ms per frame, or 22 RPS, on an 8x B200 GPU node and yields significantly better visual quality and realism. We show that FastFrames enables real-time interaction in applications such as camera-conditioned and physics-conditioned video generation.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.