Diffusion Image Editing via Asynchronous Token Decoding
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8887-8895
Abstract
Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, na\''ively switching the text condition during sampling often causes global drift, as denoising dynamics propagate changes across tokens and can disrupt unedited regions. To address this issue, we propose Asynchronous Token Decoding Edit (ATDEdit), an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix and enables token-indexed condition switching with differentiated update policies. Instead of applying synchronous target-conditioned updates to all tokens, ATDEdit estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set. It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values; these operations promote background preservation but do not constitute a pixel-level invariance guarantee. This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning. On PIE-Bench, ATDEdit achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS, while retaining competitive semantic alignment.Keywords
Funding Information
- Guangdong Basic and Applied Basic Research Foundation (2025A1515110445)
- National Training Program of Innovation and Entrepreneurship for Undergraduates (202511845040)
- Guangdong University of Technology Training Program of Research for Undergraduates (xj2026118450535)
This publication has 14 references indexed in Scilit:
- Stable Flow: Vital Layers for Training-Free Image Editing2025
- TokenCompose: Text-to-Image Diffusion with Token-Level Supervision2024
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing2023
- Scalable Diffusion Models with Transformers2023
- Null-text Inversion for Editing Real Images using Guided Diffusion Models2023
- Imagic: Text-Based Real Image Editing with Diffusion Models2023
- InstructPix2Pix: Learning to Follow Image Editing Instructions2023
- Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018