Research map / Image generation / Text-to-image diffusion
Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
Ruidong Chen, Yancheng Bai, Xuanpu Zhang, Jianhao Zeng, Lanjun Wang, Dan Song, Lei Sun, Xiangxiang Chu, Anan Liu
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 Hard Binding (with LSN) (ablation) | LayerBind (FLUX) · BindBench | VQAScore: 43.65 -> 52.55 | Improved |
| add Hard Binding (without LSN) (ablation) | LayerBind (FLUX) · BindBench | VQAScore: 38.36 -> 50.98 | Improved |
| add Layer-wise Semantic Nursing (without HB) (ablation) | LayerBind (FLUX) · BindBench | VQAScore: 38.36 -> 43.65 | Improved |
| add Layer-wise Semantic Nursing (with HB) (ablation) | LayerBind (FLUX) · BindBench | VQAScore: 50.98 -> 52.55 | Improved |
| add Layer-wise Semantic Nursing (with HB) (ablation) | LayerBind (FLUX) · BindBench | HPS: 29.64 -> 29.66 | No clear effect |
| add Layer-wise Semantic Nursing (with HB) (ablation) | LayerBind (FLUX) · BindBench | CLIP_G: 35.78 -> 35.72 | No clear effect |
| add Hard Binding (without LSN) (ablation) | LayerBind (FLUX) · BindBench | HPS: 28.27 -> 29.64 | Improved |
| add Layer-wise Semantic Nursing (without HB) (ablation) | LayerBind (FLUX) · BindBench | HPS: 28.27 -> 28.64 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.
- InstanceDiffusion — InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024) · better on 2 of 2 shared results
- CreatiDesign — CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design (ICLR 2026) · better on 0 of 1 shared result
- RAGD — RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation (ICCV 2025) · better on 0 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
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.89)
- InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024 · similarity 0.89)
- Control and Realism: Best of Both Worlds in Layout-to-Image without Training (ICML 2025 · similarity 0.88)
- Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing (CVPR 2024 · similarity 0.88)
- Local Conditional Controlling for Text-to-Image Diffusion Models (AAAI 2025 · similarity 0.88)
- Towards Transformer-Based Aligned Generation with Self-Coherence Guidance (CVPR 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.
