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

Source: https://huggingface.co/papers/2608.20910 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

InfinityEdit enables continuous, unbounded video editing by using a lightweight adapter with history, temporal causal, and edit cross-attention modules to extend edits into future streaming frames while maintaining stability.

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 itinfinite 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 forinfinite video editing. Based on the collected data, we propose InfinityEdit, a lightweightedit adapterthat equips astreaming video generatorwith unbounded editing ability. The adapter contains three attention modules.History cross-attentionguides thedenoisingframes using the input frames.Temporal causal self-attentionkeeps temporal cues flowing only from earlier frames to later ones.Edit cross-attentioninjects 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 resetanchor 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.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.20910

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.20910 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.20910 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.20910 in a Space README.md to link it from this page.

Collections including this paper1