AI Paper Atlas

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

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Hui Zhang, Dexiang Hong, Yitong Wang, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 45 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 layout guidance with a cross-attention layout adapter (ablation)SD3 · LayoutSAM-EvalSpatial: 78.70 -> 88.43Improved
add layout as joint modality in M3-Attention (ablation)SD3 · LayoutSAM-EvalSpatial: 78.70 -> 79.15No clear effect
decouple M3-Attention into parallel image-text and image-layout branches (SiamLayout) (ablation)SD3 with M3-Attention · LayoutSAM-EvalSpatial: 79.15 -> 92.67Improved
use SiamLayout instead of layout adapter (ablation)SD3 with layout adapter · LayoutSAM-EvalSpatial: 88.43 -> 92.67Improved
use SiamLayout instead of layout adapter (ablation)SD3 with layout adapter · LayoutSAM-EvalTexture: 73.56 -> 77.21Improved
add layout guidance to SD3 on T2I-CompBench via LLM planned layoutsSD3 · T2I-CompBenchSpatial: 32.00 -> 47.36Improved
add layout guidance to SD3SD3 · T2I-CompBenchShape: 58.85 -> 61.32Improved
add region-aware loss (ablation)SiamLayout training · LayoutSAMconvergence speedImproved
add biased time step sampling toward larger steps (ablation)SiamLayout training · LayoutSAMconvergence speedImproved
fine-tune Llama3.1 into LayoutDesigner (SFT) for caption-to-layoutLlama3.1-8b-it · Layout planning (global caption)accuracy: +49.89Improved
fine-tune Llama3.1 into LayoutDesigner (SFT) for layout optimizationLlama3.1-8b-it · Layout planning (center point)accuracy: +26.65Improved
use SiamLayout instead of InstanceDiffusion on coarse COCOlayout-to-image · COCO 2017AP: 51.9 -> 47.8Hurt

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