FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors

TL;DR

FramePainter leverages video diffusion priors for efficient, coherent, and seamless interactive image editing, reducing training costs and enhancing generalization to unseen scenarios.

Contribution

It reformulates image editing as an image-to-video generation task, introducing a lightweight control encoder and matching attention to improve temporal consistency and handle large motions.

Findings

Outperforms previous methods with less training data

Achieves highly seamless and coherent image edits

Demonstrates strong generalization to unseen scenarios

Abstract

Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with various physical interactions. However, these models are usually built upon text-to-image diffusion models, so necessitate (i) massive training samples and (ii) an additional reference encoder to learn real-world dynamics and visual consistency. In this paper, we reformulate this task as an image-to-video generation problem, so that inherit powerful video diffusion priors to reduce training costs and ensure temporal consistency. Specifically, we introduce FramePainter as an efficient instantiation of this formulation. Initialized with Stable Video Diffusion, it only uses a lightweight sparse control encoder to inject editing signals. Considering the limitations of temporal attention in handling large motion between two frames, we further propose matching attention to enlarge the receptive field while encouraging dense correspondence between edited and source image tokens. We highlight the effectiveness and efficiency of FramePainter across various of editing signals: it domainantly outperforms previous state-of-the-art methods with far less training data, achieving highly seamless and coherent editing of images, \eg, automatically adjust the reflection of the cup. Moreover, FramePainter also exhibits exceptional generalization in scenarios not present in real-world videos, \eg, transform the clownfish into shark-like shape. Our code will be available at https://github.com/YBYBZhang/FramePainter.