Video4Edit: Viewing Image Editing as a Degenerate Temporal Process

TL;DR

Video4Edit introduces a novel perspective by modeling image editing as a degenerate temporal process, leveraging video pre-training to achieve efficient and high-quality image editing with minimal supervision.

Contribution

It proposes a new temporal modeling approach for image editing, reducing data requirements by transferring priors from video pre-training.

Findings

Matches performance of leading baselines

Uses only about 1% of the supervision needed by mainstream models

Achieves high-quality editing with efficient fine-tuning

Abstract

We observe that recent advances in multimodal foundation models have propelled instruction-driven image generation and editing into a genuinely cross-modal, cooperative regime. Nevertheless, state-of-the-art editing pipelines remain costly: beyond training large diffusion/flow models, they require curating massive high-quality triplets of \{instruction, source image, edited image\} to cover diverse user intents. Moreover, the fidelity of visual replacements hinges on how precisely the instruction references the target semantics. We revisit this challenge through the lens of temporal modeling: if video can be regarded as a full temporal process, then image editing can be seen as a degenerate temporal process. This perspective allows us to transfer single-frame evolution priors from video pre-training, enabling a highly data-efficient fine-tuning regime. Empirically, our approach matches the performance of leading open-source baselines while using only about one percent of the supervision demanded by mainstream editing models.