From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

• URL: http://arxiv.org/abs/2412.07772v2
• Date: Mon, 06 Jan 2025 01:26:42 GMT
• Title: From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
• Authors: Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang,
• Abstract summary: Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
• Score: 52.32078428442281
• License:
• Abstract: Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models. It enables fast streaming generation of high-quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner. We will release the code based on an open-source model in the future.

Related papers

• Single Trajectory Distillation for Accelerating Image and Video Style Transfer [22.304420035048942]
  Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. We propose single trajectory distillation (STD) starting from a specific partial noise state. Our method surpasses existing acceleration models in terms of style similarity and aesthetic evaluations.
  arXiv  Detail & Related papers  (2024-12-25T16:40:23Z)
• DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization [50.30051934609654]
  We introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation. Our method demonstrates state-of-the-art performance in few-step generation for 10-second videos (128 frames at 12 FPS) One-step distillation accelerates the teacher model's diffusion sampling by up to 278.6 times, enabling near real-time generation.
  arXiv  Detail & Related papers  (2024-12-20T09:07:36Z)
• Autoregressive Video Generation without Vector Quantization [90.87907377618747]
  We reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity.
  arXiv  Detail & Related papers  (2024-12-18T18:59:53Z)
• FrameBridge: Improving Image-to-Video Generation with Bridge Models [23.19370431940568]
  Image-to-video (I2V) generation is gaining increasing attention with its wide application in video synthesis. We present FrameBridge, taking the given static image as the prior of video target and establishing a tractable bridge model between them. We propose two techniques, SNR- Fine-tuning (SAF) and neural prior, which improve the fine-tuning efficiency of diffusion-based T2V models to FrameBridge and the synthesis quality of bridge-based I2V models respectively.
  arXiv  Detail & Related papers  (2024-10-20T12:10:24Z)
• Pyramidal Flow Matching for Efficient Video Generative Modeling [67.03504440964564]
  This work introduces a unified pyramidal flow matching algorithm. It sacrifices the original denoising trajectory as a series of pyramid stages, where only the final stage operates at the full resolution. The entire framework can be optimized in an end-to-end manner and with a single unified Diffusion Transformer (DiT)
  arXiv  Detail & Related papers  (2024-10-08T12:10:37Z)
• AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction [88.70116693750452]
  Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction. Previous TVP methods make significant breakthroughs by adapting Stable Diffusion for this task. We introduce the Multi-Modal Large Language Model (MLLM) to predict future video states based on initial frames and text instructions.
  arXiv  Detail & Related papers  (2024-06-10T17:02:08Z)
• SF-V: Single Forward Video Generation Model [57.292575082410785]
  We propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained models. Experiments demonstrate that our method achieves competitive generation quality of synthesized videos with significantly reduced computational overhead.
  arXiv  Detail & Related papers  (2024-06-06T17:58:27Z)

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.