LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fu, Wingwa, Okatani, Takayuki
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909982616715264
author Fu, Wingwa
Okatani, Takayuki
author_facet Fu, Wingwa
Okatani, Takayuki
contents Text-to-Image editing using diffusion models faces challenges in balancing content preservation with edit application and handling real-image editing. To address these, we propose LAMS-Edit, leveraging intermediate states from the inversion process--an essential step in real-image editing--during edited image generation. Specifically, latent representations and attention maps from both processes are combined at each step using weighted interpolation, controlled by a scheduler. This technique, Latent and Attention Mixing with Schedulers (LAMS), integrates with Prompt-to-Prompt (P2P) to form LAMS-Edit--an extensible framework that supports precise editing with region masks and enables style transfer via LoRA. Extensive experiments demonstrate that LAMS-Edit effectively balances content preservation and edit application.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02987
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing
Fu, Wingwa
Okatani, Takayuki
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-to-Image editing using diffusion models faces challenges in balancing content preservation with edit application and handling real-image editing. To address these, we propose LAMS-Edit, leveraging intermediate states from the inversion process--an essential step in real-image editing--during edited image generation. Specifically, latent representations and attention maps from both processes are combined at each step using weighted interpolation, controlled by a scheduler. This technique, Latent and Attention Mixing with Schedulers (LAMS), integrates with Prompt-to-Prompt (P2P) to form LAMS-Edit--an extensible framework that supports precise editing with region masks and enables style transfer via LoRA. Extensive experiments demonstrate that LAMS-Edit effectively balances content preservation and edit application.
title LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.02987