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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Bridge Image Tokens for hard text binding (vs naive isolation) (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 48.5 -> 71.9 | Improved |
| add Bridge Image Tokens for hard text binding (vs naive isolation) (ablation) | DreamRenderer · COCO-MIG | Image Success Ratio: 12.5 -> 37.1 | Improved |
| add Hard Text Attribute Binding (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 67.2 -> 71.9 | Improved |
| add Hard Text Attribute Binding (ablation) | DreamRenderer · COCO-MIG | Image Success Ratio: 29.5 -> 37.1 | Improved |
| add Hard Text Attribute Binding, 2 to 6 instances (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 3.5% to 6.2% | Improved |
| add hard image binding in middle layers (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 56.2 -> 71.9 | Improved |
| apply hard image binding in input layers instead of none (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 56.2 -> 57.1 | No clear effect |
| apply hard image binding in output layers instead of none (ablation) | DreamRenderer · COCO-MIG | Instance Success Ratio: 56.2 -> 57.6 | No clear effect |
| apply hard image binding in output layers instead of none (ablation) | DreamRenderer · COCO-MIG | Image Success Ratio: 23.6 -> 20.0 | Hurt |
| apply hard image binding in input layers instead of none (ablation) | DreamRenderer · COCO-MIG | Image Success Ratio: 23.6 -> 22.5 | Hurt |
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.
- InstanceControl: Controllable Complex Image Generation without Instance Labeling (ECCV 2026 · better on 1 of 1 shared result)
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.
- InstanceDiffusion — InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024) · better on 2 of 2 shared results
- MIGC — MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024) · better on 2 of 2 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
- ROICtrl: Boosting Instance Control for Visual Generation (CVPR 2025 · similarity 0.87)
- Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis (NeurIPS 2024 · similarity 0.87)
- InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024 · similarity 0.87)
- Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions (CVPR 2025 · similarity 0.87)
- MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024 · similarity 0.86)
- Localizing and Editing Knowledge In Text-to-Image Generative Models (ICLR 2024 · similarity 0.86)
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.
