Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ji, Liya, Qi, Chenyang, Chen, Qifeng
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.22624
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911469934739456
author Ji, Liya
Qi, Chenyang
Chen, Qifeng
author_facet Ji, Liya
Qi, Chenyang
Chen, Qifeng
contents Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large language models, object segmentation models, and editing models for this task. However, the understanding models provide only a single modality ability, restricting the editing quality. We aim to bridge understanding and generation via a new multi-modality model that provides the intelligent abilities to instruction-based image editing models for more complex cases. To achieve this goal, we individually separate the instruction editing task with the multi-modality chain of thought prompts, i.e., Chain-of-Thought (CoT) planning, editing region reasoning, and editing. For Chain-of-Thought planning, the large language model could reason the appropriate sub-prompts considering the instruction provided and the ability of the editing network. For editing region reasoning, we train an instruction-based editing region generation network with a multi-modal large language model. Finally, a hint-guided instruction-based editing network is proposed for editing image generations based on the sizeable text-to-image diffusion model to accept the hints for generation. Extensive experiments demonstrate that our method has competitive editing abilities on complex real-world images.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22624
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Instruction-based Image Editing with Planning, Reasoning, and Generation
Ji, Liya
Qi, Chenyang
Chen, Qifeng
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10
Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large language models, object segmentation models, and editing models for this task. However, the understanding models provide only a single modality ability, restricting the editing quality. We aim to bridge understanding and generation via a new multi-modality model that provides the intelligent abilities to instruction-based image editing models for more complex cases. To achieve this goal, we individually separate the instruction editing task with the multi-modality chain of thought prompts, i.e., Chain-of-Thought (CoT) planning, editing region reasoning, and editing. For Chain-of-Thought planning, the large language model could reason the appropriate sub-prompts considering the instruction provided and the ability of the editing network. For editing region reasoning, we train an instruction-based editing region generation network with a multi-modal large language model. Finally, a hint-guided instruction-based editing network is proposed for editing image generations based on the sizeable text-to-image diffusion model to accept the hints for generation. Extensive experiments demonstrate that our method has competitive editing abilities on complex real-world images.
title Instruction-based Image Editing with Planning, Reasoning, and Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10
url https://arxiv.org/abs/2602.22624