Papers › FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

18 Apr 2024arXiv:2404.11895archive 2025-07-28

Wei Wu, Qingnan Fan, Shuai Qin, Hong Gu, Ruoyu Zhao, Antoni B. Chan

Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature. However, such attempts face the pivotal challenge of misalignment between the intended precise editing target regions and the broader area impacted by the guidance in practice. Despite excellent methods leveraging attention mechanisms that have been developed to refine the editing guidance, these approaches necessitate modifications through complex network architecture and are limited to specific editing tasks. In this work, we re-examine the diffusion process and misalignment problem from a frequency perspective, revealing that, due to the power law of natural images and the decaying noise schedule, the denoising network primarily recovers low-frequency image components during the earlier timesteps and thus brings excessive low-frequency signals for editing. Leveraging this insight, we introduce a novel fine-tuning free approach that employs progressive Frequency truncation to refine the guidance of Diffusion models for universal editing tasks (FreeDiff). Our method achieves comparable results with state-of-the-art methods across a variety of editing tasks and on a diverse set of images, highlighting its potential as a versatile tool in image editing applications.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thermal-dynamics/freediff officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Denoising

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections