Paper Image

Text and image guided image editing

Published on:

28 March 2024

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Yulin Pan,

Chaojie Mao,

Zeyinzi Jiang,

Zhen Han,

Jingfeng Zhang


Key Details

Employs noise concatenation for precise region editing

Uses decoupled cross-attention for multi-modal guidance

Introduces RefineNet to supplement subject details

Constructs training data from images using CV models

Excels at identity and text consistency

Explore the topics in this paper

AI generated summary

Text and image guided image editing

This paper presents a new approach called LAR-Gen that enables seamless editing of masked areas in images using both text prompts and reference images as guidance. It uses a coarse-to-fine pipeline to ensure fidelity.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up