Playing with Transformer at 30+ FPS via Next-Frame Diffusion

• URL: http://arxiv.org/abs/2506.01380v2
• Date: Fri, 04 Jul 2025 14:56:46 GMT
• Title: Playing with Transformer at 30+ FPS via Next-Frame Diffusion
• Authors: Xinle Cheng, Tianyu He, Jiayi Xu, Junliang Guo, Di He, Jiang Bian,
• Abstract summary: Next-Frame Diffusion (NFD) is an autoregressive diffusion transformer that incorporates block-wise causal attention.<n>We show that NFD beats autoregressive baselines in terms of both visual quality and sampling efficiency.<n>We achieve autoregressive video generation at over 30 Frames Per Second (FPS) on an A100 GPU using a 310M model.
• Score: 40.04104312955399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame. Nonetheless, achieving real-time video generation remains a significant challenge for such models, primarily due to the high computational cost associated with diffusion sampling and the hardware inefficiencies inherent to autoregressive generation. To address this, we introduce two innovations: (1) We extend consistency distillation to the video domain and adapt it specifically for video models, enabling efficient inference with few sampling steps; (2) To fully leverage parallel computation, motivated by the observation that adjacent frames often share the identical action input, we propose speculative sampling. In this approach, the model generates next few frames using current action input, and discard speculatively generated frames if the input action differs. Experiments on a large-scale action-conditioned video generation benchmark demonstrate that NFD beats autoregressive baselines in terms of both visual quality and sampling efficiency. We, for the first time, achieves autoregressive video generation at over 30 Frames Per Second (FPS) on an A100 GPU using a 310M model.

Related papers

• StreamDiT: Real-Time Streaming Text-to-Video Generation [40.441404889974294]
  This paper proposes StreamDiT, a streaming video generation model.<n>StreamDiT training is based on flow matching by adding a moving buffer.<n>We design mixed training with different partitioning schemes of buffered frames to boost both content consistency and visual quality.<n>Our model enables real-time applications, e.g. streaming generation, interactive generation, and video-to-video.
  arXiv  Detail & Related papers  (2025-07-04T18:00:01Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [52.32078428442281]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)
• Optical-Flow Guided Prompt Optimization for Coherent Video Generation [51.430833518070145]
  We propose a framework called MotionPrompt that guides the video generation process via optical flow.<n>We optimize learnable token embeddings during reverse sampling steps by using gradients from a trained discriminator applied to random frame pairs.<n>This approach allows our method to generate visually coherent video sequences that closely reflect natural motion dynamics, without compromising the fidelity of the generated content.
  arXiv  Detail & Related papers  (2024-11-23T12:26:52Z)
• ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler [53.98558445900626]
  Current image-to-video diffusion models, while powerful in generating videos from a single frame, need adaptation for two-frame conditioned generation.<n>We introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning.<n>Our method employs sequential sampling along both forward and backward paths, conditioned on the start and end frames, respectively, ensuring more coherent and on-manifold generation of intermediate frames.
  arXiv  Detail & Related papers  (2024-10-08T03:01:54Z)
• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [64.2445487645478]
  Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio. We present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation.
  arXiv  Detail & Related papers  (2024-07-11T17:34:51Z)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.