DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models

ICLR 2026 Conference Submission10302 Authors

Keywords: Video Editing, Diffusion Models, Video Generation, Parameter-Efficient Fine-Tuning

Abstract: Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and training-free methods. While training-based methods incur high computational costs, training-free alternatives yield suboptimal performance. To address these limitations, we propose DAPE, a high-quality yet cost-effective two-stage parameter-efficient fine-tuning (PEFT) framework for video editing. In the first stage, we design an efficient norm-tuning method to enhance temporal consistency in generated videos. The second stage introduces a vision-friendly adapter to improve visual quality. Additionally, we identify critical shortcomings in existing benchmarks including limited category diversity, imbalanced object distribution, and inconsistent frame counts. To mitigate these issues, we curate a high-quality dataset benchmark comprising more videos with rich annotations and editing prompts, enabling objective and comprehensive evaluation of advanced methods. Extensive experiments on existing datasets (BalanceCC, loveu-tgve, RAVE) and our proposed benchmark demonstrate that DAPE significantly improves temporal coherence and text-video alignment while outperforming previous state-of-the-art approaches. We will release the code and dataset in the final version.

Primary Area: generative models

Submission Number: 10302