InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter

• URL: http://arxiv.org/abs/2608.20910v1
• Date: Fri, 21 Aug 2026 09:27:49 GMT
• Title: InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter
• Abstract summary: We propose a lightweight edit adapter for infinite video editing.<n>It applies an edit while preserving the original model's infinite generation ability.<n>Experiments show that InfinityEdit faithfully continues the stream under each edit, and stays stable over edit sequences.
• Score: 25.43582750863899
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place editing assumption. They align the edited video with the given source clip frame by frame over a fixed time span. This pattern fails for open-ended streams, e.g., restyling a live game or applying a camera move to an ongoing shot. In such cases, edits must extend to future frames as they arrive, rather than be applied to a static input clip. In this paper, we study this setting and name it infinite video editing: given a preceding segment and an edit request, a model must generate the next segment that continues the stream while applying the requested edit. This process repeats as an unbounded sequence of edit instructions arrives. This task brings two challenges: the edit must be a faithful continuation rather than a frame-wise rewrite, and generation quality must remain stable as edits accumulate. To address them, we first design a data-collection pipeline for infinite video editing. Based on the collected data, we propose InfinityEdit, a lightweight edit adapter that equips a streaming video generator with unbounded editing ability. The adapter contains three attention modules. History cross-attention guides the denoising frames using the input frames. Temporal causal self-attention keeps temporal cues flowing only from earlier frames to later ones. Edit cross-attention injects the edit request into generation. During inference, the adapter is activated only in the chunk where an edit request arrives. Subsequent chunks are generated by the original model with a reset anchor frame. This scheme applies the edit while preserving the original model's infinite generation ability. Extensive experiments show that InfinityEdit faithfully continues the stream under each edit, and stays stable over unbounded edit sequences.

Related papers

• Instruction-Based Video Editing by Repurposing an Image Editing Model [55.9214783600876]
  We show that a strong instruction-based image editing model can edit videos by operating directly on video-VAE latents.<n>Our results suggest that, despite the large investment in training video latent spaces, per-frame video latents remain close enough to the image domain that mature image editing priors transfer with minimal adaptation.
  arXiv  Detail & Related papers  (2026-08-14T18:01:29Z)
• AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance [42.3107762497025]
  Video generative models have achieved remarkable progress in synthesizing video sequences.<n>Fine-grained instance-level video editing, including object insertion, object removal, and texture editing, has emerged as a prominent yet challenging problem.<n>We propose AlbedoEdit, a unified generative video editing framework that jointly supports object insertion, object removal, and texture editing.
  arXiv  Detail & Related papers  (2026-05-31T17:33:14Z)
• EasyV2V: A High-quality Instruction-based Video Editing Framework [108.78294392167017]
  captionemphEasyV2V is a framework for instruction-based video editing.<n>EasyV2V works with flexible inputs, e.g., video+text, video+mask+reference+, and state-of-the-art video editing results.
  arXiv  Detail & Related papers  (2025-12-18T18:59:57Z)
• FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing [52.54102743380658]
  We propose FlowDC, which decouples the complex editing into multiple sub-editing effects and superposes them in parallel during the editing process.<n>FlowDC shows superior results compared with existing methods.
  arXiv  Detail & Related papers  (2025-12-12T09:08:39Z)
• UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing [28.140945021777878]
  We present UniEdit, a tuning-free framework that supports both video motion and appearance editing. To realize motion editing while preserving source video content, we introduce auxiliary motion-reference and reconstruction branches. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers.
  arXiv  Detail & Related papers  (2024-02-20T17:52:12Z)
• RealCraft: Attention Control as A Tool for Zero-Shot Consistent Video Editing [9.215070588761282]
  We propose RealCraft, an attention-control-based method for zero-shot real-world video editing.<n>By swapping cross-attention for new feature injection and relaxing spatial-temporal attention of the editing object, we achieve localized shape-wise edit.<n>We showcase the proposed zero-shot attention-control-based method across a range of videos, demonstrating shape-wise, time-consistent and parameter-free editing.
  arXiv  Detail & Related papers  (2023-12-19T22:33:42Z)
• Neural Video Fields Editing [56.558490998753456]
  NVEdit is a text-driven video editing framework designed to mitigate memory overhead and improve consistency. We construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames. Next, we update the video field through off-the-shelf Text-to-Image (T2I) models to text-driven editing effects.
  arXiv  Detail & Related papers  (2023-12-12T14:48:48Z)
• Neutral Editing Framework for Diffusion-based Video Editing [24.370584544151424]
  This paper proposes Neutral Editing (NeuEdit) framework to enable complex non-rigid editing. NeuEdit introduces a concept of neutralization' that enhances a tuning-editing process of diffusion-based editing systems. Experiments on numerous videos demonstrate adaptability and effectiveness of the NeuEdit framework.
  arXiv  Detail & Related papers  (2023-12-10T16:28:32Z)
• MotionEditor: Editing Video Motion via Content-Aware Diffusion [96.825431998349]
  MotionEditor is a diffusion model for video motion editing. It incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence.
  arXiv  Detail & Related papers  (2023-11-30T18:59:33Z)
• MagicEdit: High-Fidelity and Temporally Coherent Video Editing [70.55750617502696]
  We present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. We found that high-fidelity and temporally coherent video-to-video translation can be achieved by explicitly disentangling the learning of content, structure and motion signals during training.
  arXiv  Detail & Related papers  (2023-08-28T17:56:22Z)

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.