AI Paper Atlas

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

IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation

Yinwei Wu, Xianpan Zhou, Bing Ma, Xuefeng Su, Kai Ma, Xinchao Wang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 27 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 appearance tokens (ablation)IFAdapter · COCO IFG benchmarkIFS rate (QwenVL): 69.6 -> 79.7Improved
add appearance tokens (ablation)IFAdapter · COCO IFG benchmarkIFS rate (CogVL): 53.5 -> 61.0Improved
add appearance tokens (ablation)IFAdapter · COCO IFG benchmarkFID: 27.2 -> 22.0Improved
add appearance tokens (ablation)IFAdapter · COCO IFG benchmarkGrounding-DINO AP: 45.9 -> 49.0Improved
add appearance tokens (CLIP score is lower without them) (ablation)IFAdapter · COCO IFG benchmarkCLIP score: 24.1 -> 25.1Improved
add EoT token (ablation)IFAdapter · COCO IFG benchmarkIFS rate (QwenVL): 29.9 -> 79.7Improved
add EoT token (ablation)IFAdapter · COCO IFG benchmarkFID: 44.7 -> 22.0Improved
add EoT token (ablation)IFAdapter · COCO IFG benchmarkGrounding-DINO AP: 12.3 -> 49.0Improved
IFAdapter vs InstanceDiffusionIFAdapter · COCO IFG benchmarkIFS rate (QwenVL): 69.6 -> 79.7Improved
IFAdapter vs InstanceDiffusionIFAdapter · COCO IFG benchmarkFID: 26.8 -> 22.0Improved
IFAdapter vs InstanceDiffusionIFAdapter · COCO IFG benchmarkGrounding-DINO AP: 43.1 -> 49.0Improved
IFAdapter vs InstanceDiffusionIFAdapter · User studyinstance details score: 3.82 -> 4.69Improved

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