Research map / Image generation / Text-to-image diffusion
FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting
Chao Gong, Dong Li, Yingwei Pan, Jingjing Chen, Ting Yao, Tao Mei
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 PriNo initial-noise optimization (ablation) | BrushNet · EditBench | ImageReward: 0.2729 -> 0.3785 | Improved |
| add PriNo initial-noise optimization (ablation) | BrushNet · EditBench | InpaintReward: -0.1791 -> -0.2124 | Hurt |
| add DeGu decomposed guidance (ablation) | BrushNet · EditBench | InpaintReward: -0.1791 -> -0.0643 | Improved |
| combine PriNo and DeGu (ablation) | BrushNet · EditBench | ImageReward: 0.3785/0.3908 -> 0.5006 | Improved |
| use sqrt(alpha_bar_t) modulator instead of constant (ablation) | FreeInpaint · EditBench | ImageReward: 0.3533 -> 0.5006 | Improved |
| use sqrt(alpha_bar_t) modulator instead of sqrt(1-alpha_bar_t) (ablation) | FreeInpaint · EditBench | ImageReward: 0.3454 -> 0.5006 | Improved |
| add FreeInpaint | SDXL-Inpainting · EditBench | LPIPS: 0.2826 -> 0.2087 | Improved |
| add HD-Painter | SDXL-Inpainting · EditBench | LPIPS: 0.2826 -> 0.3206 | Hurt |
| add HD-Painter | SD3-ControlNet-Inpainting · EditBench | ImageReward: 0.2993 -> -0.5020 | Hurt |
| add FreeInpaint | SD3-ControlNet-Inpainting · EditBench | ImageReward: 0.2993 -> 0.5248 | Improved |
| add FreeInpaint | SD1.5-Inpainting · MSCOCO (layout masks) | ImageReward: 0.2574 -> 0.2591 | No clear effect |
| add FreeInpaint | BrushNet · MSCOCO (layout masks) | Local CLIP: 24.51 -> 24.69 (HDP 24.87) | Mixed |
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.
- +HD-Painter — HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025) · better on 10 of 10 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
- HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025 · similarity 0.90)
- PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference (NeurIPS 2024 · similarity 0.90)
- One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting (NeurIPS 2025 · similarity 0.89)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · similarity 0.89)
- MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting (CVPR 2025 · similarity 0.88)
- DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework (AAAI 2025 · similarity 0.88)
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.
