Research map / Image generation / Text-to-image diffusion
ConsistCompose: Unified Multimodal Layout Control for Image Composition
Xuanke Shi, Boxuan Li, Xiaoyang Han, Zhongang Cai, Lei Yang, Quan Wang, Dahua Lin
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 coordinate tokens to the generation training (Coord vs w/o Coord) (ablation) | ConsistCompose · MMMU | accuracy: 39.4 -> 42.3 | Improved |
| add coordinate setting to training (Coord vs w/o Coord) (ablation) | ConsistCompose · GEdit | score: 6.23 -> 6.31 | Improved |
| add coordinate setting to training (Coord vs w/o Coord) (ablation) | ConsistCompose · MMBench | score: 81.5 -> 81.4 | No clear effect |
| layout-aware LELG training on top of Bagel | Bagel · MMMU | accuracy: 46.4 -> 42.3 | Hurt |
| layout-aware LELG training on top of Bagel | Bagel · MMBench | score: 81.4 -> 81.4 | No clear effect |
| layout-aware LELG training on top of Bagel | Bagel · GEdit | score: 6.68 -> 6.31 | Hurt |
| layout-aware LELG training on top of Bagel | Bagel · GenEval | score: 0.86 -> 0.88 | Improved |
| increase Coordinate-CFG scale from 0.2 to 0.6 (ablation) | ConsistCompose · MS-Bench-Random | DINO: 0.497 -> 0.630 | Improved |
| increase Coordinate-CFG scale from 0.2 to 0.6 (ablation) | ConsistCompose · MS-Bench-Random | mIoU (%): 41.7% -> 87.8% | Improved |
| increase Coordinate-CFG scale further from 0.6 to 1.4 (ablation) | ConsistCompose · MS-Bench-Random | DINO: 0.630 -> 0.589 | Hurt |
| increase Coordinate-CFG scale from 0.2 to 1.4 (ablation) | ConsistCompose · COCO-Position | mIoU/AP | Improved |
| increase Coordinate-CFG scale beyond 2.0 (ablation) | ConsistCompose · COCO-Position | perceptual quality | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- InstanceDiffusion — InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024) · better on 5 of 5 shared results
- MIGC++ — MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024) · better on 2 of 2 shared results
- MS-Diffusion — MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance (ICLR 2025) · better on 0 of 1 shared result
- PlanGen — PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models (ICCV 2025) · better on 1 of 1 shared result
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
- Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models (NeurIPS 2026 · similarity 0.92)
- InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention (NeurIPS 2025 · similarity 0.90)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.90)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.88)
- LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration (NeurIPS 2025 · similarity 0.88)
- HDLayout: Hierarchical and Directional Layout Planning for Arbitrary Shaped Visual Text Generation (AAAI 2025 · similarity 0.88)
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.
