AI Paper Atlas

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

RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation

Zhennan Chen, Yajie Li, Haofan Wang, Zhibo Chen, Zhengkai Jiang, Jun Li, Qian Wang, Jian Yang, Ying Tai

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 6 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 regional soft refinement on top of hard binding (ablation)RAGD on Flux.1-dev · T2ICompBenchVQAScore: 0.7656 -> 0.8907Improved
add regional hard binding on top of soft refinement (ablation)RAGD on Flux.1-dev · T2ICompBenchSpatial: 0.4939 -> 0.5193Improved
add hard binding on top of soft refinement (ablation)RAGD on Flux.1-dev · T2ICompBenchVQAScore: 0.8413 -> 0.8907Improved
add soft refinement to hard binding (ablation)RAGD on Flux.1-dev · T2ICompBenchSpatial: 0.2821 -> 0.5193Improved
apply RAGD to SD3.5 instead of baseline SD3.5SD3.5 · T2ICompBenchVQAScore: 0.8393 -> 0.8543Improved
apply RAGD to Flux instead of baseline FluxFlux.1-dev · T2ICompBenchVQAScore: 0.7438 -> 0.8907Improved
apply RPG to SD3.5 instead of baseline SD3.5SD3.5 · T2ICompBenchVQAScore: 0.8393 -> 0.8340Hurt
apply RPG to SD3.5 and Flux, color attributeSD3.5 and Flux · T2ICompBenchColor: 0.7870 -> 0.7343 (SD3.5); 0.7680 -> 0.7033 (Flux)Hurt
combine RAGD with Hyper-Flux accelerationRAGD · Inference speedspeedup: 2.5x fasterImproved
increase number of regions in RAGDRAGD · Inference timeinference timeHurt

Later papers that compared with this method

1 later accepted paper reports RAGD as a baseline in their results tables; 0 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