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
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 appearance tokens (ablation) | IFAdapter · COCO IFG benchmark | IFS rate (QwenVL): 69.6 -> 79.7 | Improved |
| add appearance tokens (ablation) | IFAdapter · COCO IFG benchmark | IFS rate (CogVL): 53.5 -> 61.0 | Improved |
| add appearance tokens (ablation) | IFAdapter · COCO IFG benchmark | FID: 27.2 -> 22.0 | Improved |
| add appearance tokens (ablation) | IFAdapter · COCO IFG benchmark | Grounding-DINO AP: 45.9 -> 49.0 | Improved |
| add appearance tokens (CLIP score is lower without them) (ablation) | IFAdapter · COCO IFG benchmark | CLIP score: 24.1 -> 25.1 | Improved |
| add EoT token (ablation) | IFAdapter · COCO IFG benchmark | IFS rate (QwenVL): 29.9 -> 79.7 | Improved |
| add EoT token (ablation) | IFAdapter · COCO IFG benchmark | FID: 44.7 -> 22.0 | Improved |
| add EoT token (ablation) | IFAdapter · COCO IFG benchmark | Grounding-DINO AP: 12.3 -> 49.0 | Improved |
| IFAdapter vs InstanceDiffusion | IFAdapter · COCO IFG benchmark | IFS rate (QwenVL): 69.6 -> 79.7 | Improved |
| IFAdapter vs InstanceDiffusion | IFAdapter · COCO IFG benchmark | FID: 26.8 -> 22.0 | Improved |
| IFAdapter vs InstanceDiffusion | IFAdapter · COCO IFG benchmark | Grounding-DINO AP: 43.1 -> 49.0 | Improved |
| IFAdapter vs InstanceDiffusion | IFAdapter · User study | instance details score: 3.82 -> 4.69 | Improved |
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.
- InstanceDiffusion — InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024) · better on 6 of 6 shared results
- MIGC — MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024) · better on 4 of 4 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
- InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention (NeurIPS 2025 · similarity 0.89)
- ROICtrl: Boosting Instance Control for Visual Generation (CVPR 2025 · similarity 0.89)
- InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024 · similarity 0.89)
- SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation (AAAI 2024 · similarity 0.88)
- MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024 · similarity 0.88)
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.87)
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.
