LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning

TL;DR

LoRA-Edit introduces a mask-guided LoRA fine-tuning approach for controllable, first-frame-guided video editing, enabling precise and temporally consistent edits with user-defined transformations.

Contribution

The paper presents a novel mask-based LoRA tuning method that allows flexible, controllable video editing by teaching models to interpret masks as editing commands and synthesize consistent or novel content.

Findings

Achieves superior editing performance over baseline methods.

Enables complex transformations like object rotation and blooming.

Provides fine-grained control over temporal evolution of edits.

Abstract

Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided editing provides control over the first frame, but lacks fine-grained control over the edit's subsequent temporal evolution. To address this, we propose a mask-based LoRA (Low-Rank Adaptation) tuning method that adapts pretrained Image-to-Video models for flexible video editing. Our key innovation is using a spatiotemporal mask to strategically guide the LoRA fine-tuning process. This teaches the model two distinct skills: first, to interpret the mask as a command to either preserve content from the source video or generate new content in designated regions. Second, for these generated regions, LoRA learns to synthesize either temporally consistent motion inherited from the video or novel appearances guided by user-provided reference frames. This dual-capability LoRA grants users control over the edit's entire temporal evolution, allowing complex transformations like an object rotating or a flower blooming. Experimental results show our method achieves superior video editing performance compared to baseline methods. The code and video results are available at our project website: https://cjeen.github.io/LoRAEdit.