MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Xueyun, Li, Wei, Xu, Bingbing, Yuan, Yige, Wang, Yuanzhuo, Shen, Huawei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915412148486144
author Tian, Xueyun
Li, Wei
Xu, Bingbing
Yuan, Yige
Wang, Yuanzhuo
Shen, Huawei
author_facet Tian, Xueyun
Li, Wei
Xu, Bingbing
Yuan, Yige
Wang, Yuanzhuo
Shen, Huawei
contents Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Inspired by this, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It first treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation, then introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: by leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a SOTA in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing
Tian, Xueyun
Li, Wei
Xu, Bingbing
Yuan, Yige
Wang, Yuanzhuo
Shen, Huawei
Computer Vision and Pattern Recognition
Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Inspired by this, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It first treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation, then introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: by leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a SOTA in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.
title MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.21291