AI Paper Atlas

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

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

Dewei Zhou, Mingwei Li, Zongxin Yang, Yi Yang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 28 citations (OpenAlex)

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
add Bridge Image Tokens for hard text binding (vs naive isolation) (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 48.5 -> 71.9Improved
add Bridge Image Tokens for hard text binding (vs naive isolation) (ablation)DreamRenderer · COCO-MIGImage Success Ratio: 12.5 -> 37.1Improved
add Hard Text Attribute Binding (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 67.2 -> 71.9Improved
add Hard Text Attribute Binding (ablation)DreamRenderer · COCO-MIGImage Success Ratio: 29.5 -> 37.1Improved
add Hard Text Attribute Binding, 2 to 6 instances (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 3.5% to 6.2%Improved
add hard image binding in middle layers (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 56.2 -> 71.9Improved
apply hard image binding in input layers instead of none (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 56.2 -> 57.1No clear effect
apply hard image binding in output layers instead of none (ablation)DreamRenderer · COCO-MIGInstance Success Ratio: 56.2 -> 57.6No clear effect
apply hard image binding in output layers instead of none (ablation)DreamRenderer · COCO-MIGImage Success Ratio: 23.6 -> 20.0Hurt
apply hard image binding in input layers instead of none (ablation)DreamRenderer · COCO-MIGImage Success Ratio: 23.6 -> 22.5Hurt

Later papers that compared with this method

1 later accepted paper reports DreamRenderer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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