SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09468 · ECCV · 2024

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

closely resemble the source image. To overcome these limitations, we introduce a novel and adaptable diffusion inversion technique for real image editing, which is grounded in a theoretical analysis of the role of η in the DDIM sampling equation for enhanced editability. By designing a universal diffusion inversion method with a time-and region-dependent η function, we enable flexible control over the editing extent. Through a comprehensive series of quantitative and qualitative assessments, involving a comparison with a broad array of recent methods, we demonstrate the superiority of our approach. Our method not only sets a new benchmark in the field but also significantly outperforms existing strategies.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.09468")
get_code_for_paper("2403.09468")
have("2403.09468")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.09468.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.09468.svg)](https://syntology.ai/paper/2403.09468)

Connect an agent — have() is free.