AI Paper Atlas

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

Step-by-step Layered Design Generation

Faizan Farooq Khan, Joseph K J, Koustava Goswami, Mohamed Elhoseiny, Balaji Vasan Srinivasan

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 0 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
use SLEDGE instead of T2I+LLMGAstep-by-step design generation · IDeation Benchmarktheme adherence: 3.45 -> 3.57Improved
use SLEDGE instead of iCOLEstep-by-step design generation · IDeation Benchmarkedit compliance: 2.01 -> 3.12Improved
use SLEDGE instead of T2I+LLMGAstep-by-step design generation · Crelloedit compliance: 2.87 -> 3.60Improved
use SLEDGE instead of cCOLEfinal design quality · FIDFID: 86.7 -> 46.8Improved
use SLEDGE instead of iCOLEfinal design quality · text layoutIoU: 4.5 -> 23.5Improved
use SLEDGE instead of cCOLEfinal design quality · text renderingText Accuracy: 73.8 -> 89.4Improved
use SLEDGE instead of baselines in human studystep-by-step design generation · human evaluation, 100 samplesuser preference for theme adherence: 63%Improved
fine-tune the alignment module D instead of using the decoder after Step 1 (ablation)SLEDGE · IDeation Benchmark and CrelloMLLM-judged design qualityImproved
apply loss to the full predicted canvas instead of only the MLLM-specified region (ablation)SLEDGE · IDeation Benchmark and CrelloMLLM-judged design qualityImproved
remove optional image input U_t instead of replacing it with an empty canvas (ablation)SLEDGE · IDeation Benchmark and CrelloMLLM-judged design qualityImproved
add the layer extractor module (ablation)SLEDGE · IDeation Benchmark and CrelloMLLM-judged design qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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