AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

Ziyun Zeng, David Junhao Zhang, Wei Li, Mike Zheng Shou

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
give the editor an external CoT designer (GPT-4o) instead of the raw prompt (ablation)DIM-4.6B-Edit · ImgEditOverall: 3.10 -> 3.67Improved
use other open MLLMs as external designer instead of GPT-4o (ablation)DIM-4.6B-Edit · ImgEditOverall: 3.67 (GPT-4o) vs 3.43 to 3.59Mixed
add stage-2 fine-tuning on ShareGPT-4o-Image-CoT vs non-CoT ShareGPT-4o-Image (ablation)DIM-4.6B-Edit · ImgEditOverall: 3.22 -> 3.34Improved
stage-2 tuning on UltraEdit-160K-CoT alone (ablation)DIM-4.6B-Edit · ImgEditOverall: 2.76 -> 2.79No clear effect
combine all three CoT sources (full DIM-Edit) in stage 2 (ablation)DIM-4.6B-Edit · ImgEditOverall: 3.34 -> 3.67Improved
add Global Layout Perception step to CoT (ablation)DIM-Edit CoT · ImgEditOverall: 3.49 -> 3.67Improved
add Local Object Perception step to CoT (ablation)DIM-Edit CoT · ImgEditOverall: 3.39 -> 3.67Improved
add Edit Area Localization step to CoT (ablation)DIM-Edit CoT · ImgEditOverall: 3.42 -> 3.67Improved
add Edited Image Imagination step to CoT (ablation)DIM-Edit CoT · ImgEditOverall: 3.35 -> 3.67Improved
initialize editing model from DIM-4.6B-T2I (trained on DIM-T2I) instead of from scratch (ablation)DIM-4.6B-Edit · ImgEditOverall: 2.66 -> 3.67Improved
add ShareGPT-4o-Image to UltraEdit-4M in stage 1 (ablation)DIM-4.6B-Edit · ImgEditOverall: 2.76 -> 3.22Improved
feed DIM-style CoT blueprints as instructions to a different modelStep1X-Edit · ImgEditOverall: 3.06 -> 2.70Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy