Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

• URL: http://arxiv.org/abs/2504.12626v2
• Date: Mon, 21 Apr 2025 08:13:35 GMT
• Title: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
• Authors: Lvmin Zhang, Maneesh Agrawala,
• Abstract summary: We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation.<n>The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length.<n>We are able to process a large number of frames using video diffusion with bottleneck similar to image diffusion.
• Score: 30.77316047044662
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length. As a result, we are able to process a large number of frames using video diffusion with computation bottleneck similar to image diffusion. This also makes the training video batch sizes significantly higher (batch sizes become comparable to image diffusion training). We also propose an anti-drifting sampling method that generates frames in inverted temporal order with early-established endpoints to avoid exposure bias (error accumulation over iterations). Finally, we show that existing video diffusion models can be finetuned with FramePack, and their visual quality may be improved because the next-frame prediction supports more balanced diffusion schedulers with less extreme flow shift timesteps.

Related papers

• Generative Inbetweening through Frame-wise Conditions-Driven Video Generation [63.43583844248389]
  generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input.<n>We propose a Frame-wise Conditions-driven Video Generation (FCVG) method that significantly enhances the temporal stability of interpolated video frames.<n>Our FCVG demonstrates the capability to generate temporally stable videos using both linear and non-linear curves.
  arXiv  Detail & Related papers  (2024-12-16T13:19:41Z)
• Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction [43.16308241800144]
  We introduce a novel model class, that treats video as a continuous multi-dimensional process rather than a series of discrete frames.<n>We establish state-of-the-art performance in video prediction, validated on benchmark datasets including KTH, BAIR, Human3.6M, and UCF101.
  arXiv  Detail & Related papers  (2024-12-06T10:34:50Z)
• 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. We introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning. 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)
• ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation [81.90265212988844]
  We propose a training-free video method for generative video models in a plug-and-play manner. We transform a video model into a self-cascaded video diffusion model with the designed hidden state correction modules. Our training-free method is even comparable to trained models supported by huge compute resources and large-scale datasets.
  arXiv  Detail & Related papers  (2024-06-03T00:31:13Z)
• Aggregating Nearest Sharp Features via Hybrid Transformers for Video Deblurring [70.06559269075352]
  We propose a video deblurring method that leverages both neighboring frames and existing sharp frames using hybrid Transformers for feature aggregation.<n>To aggregate nearest sharp features from detected sharp frames, we utilize a global Transformer with multi-scale matching capability.<n>Our proposed method outperforms state-of-the-art video deblurring methods as well as event-driven video deblurring methods in terms of quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2023-09-13T16:12:11Z)
• Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation [93.18163456287164]
  This paper proposes a novel text-guided video-to-video translation framework to adapt image models to videos. Our framework achieves global style and local texture temporal consistency at a low cost.
  arXiv  Detail & Related papers  (2023-06-13T17:52:23Z)
• Optimizing Video Prediction via Video Frame Interpolation [53.16726447796844]
  We present a new optimization framework for video prediction via video frame, inspired by photo-realistic results of video framescapes. Our framework is based on optimization with a pretrained differentiable video frame module without the need for a training dataset. Our approach outperforms other video prediction methods that require a large amount of training data or extra semantic information.
  arXiv  Detail & Related papers  (2022-06-27T17:03:46Z)
• Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation [14.631523634811392]
  Masked Conditional Video Diffusion (MCVD) is a general-purpose framework for video prediction. We train the model in a manner where we randomly and independently mask all the past frames or all the future frames. Our approach yields SOTA results across standard video prediction benchmarks, with computation times measured in 1-12 days.
  arXiv  Detail & Related papers  (2022-05-19T20:58:05Z)
• SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning [40.556222166309524]
  We present SwinBERT, an end-to-end transformer-based model for video captioning. Our method adopts a video transformer to encode spatial-temporal representations that can adapt to variable lengths of video input. Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames.
  arXiv  Detail & Related papers  (2021-11-25T18:02:12Z)

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.