Research map / Image generation / Text-to-image diffusion
Co-Painter: Fine-Grained Controllable Image Stylization via Implicit Decoupling and Adaptive Injection
Bowen Fu, Wei Wei, Jiaqi Tang, Jiangtao Nie, Yanyu Ye, Xiaogang Xu, Ying-Cong Chen, Lei Zhang
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 gated feature injection (GFI) (ablation) | IP-Adapter baseline · Ablation study | TA: 14.3 -> 23.3 | Improved |
| add gated feature injection (GFI) (ablation) | IP-Adapter baseline · Ablation study | SS: 36.9 -> 31.6 | Hurt |
| add gated feature injection (GFI) (ablation) | IP-Adapter baseline · Ablation study | IQ: 6.07 -> 5.96 | Hurt |
| add fine-grained decoupling (FGD) (ablation) | IP-Adapter baseline · Ablation study | TA: 14.3 -> 24.0 | Improved |
| add fine-grained decoupling (FGD) (ablation) | IP-Adapter baseline · Ablation study | IQ: 6.07 -> 5.97 | Hurt |
| add GFI on top of FGD (ablation) | FGD · Ablation study | IQ: 5.97 -> 6.14 | Improved |
| add GFI on top of FGD (ablation) | FGD · Ablation study | SS: 29.5 -> 27.8 | Hurt |
| add FGD on top of GFI (ablation) | GFI · Ablation study | IQ: 5.96 -> 6.14 | Improved |
| add GFI to FGD (adaptive instead of static injection) (ablation) | Co-Painter (FGD) · Fine-grained stylization | BSTS: 20.1 -> 20.6 | Improved |
| use FGD instead of stacking adapters | T2I-Adapter (stacked) · Fine-grained stylization | TA: 23.5 -> 24.3 | Improved |
| use Co-Painter instead of IP-Adapter | IP-Adapter · Standard stylization | TA: 14.3 -> 24.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DEADiff — DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations (CVPR 2024) · better on 3 of 4 shared results
- T2I-Adapter — T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models (AAAI 2024) · better on 2 of 3 shared results
- StyTR-2 — StyTr2: Image Style Transfer With Transformers (CVPR 2022) · better on 2 of 3 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
- One-Shot Structure-Aware Stylized Image Synthesis (CVPR 2024 · similarity 0.88)
- DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations (CVPR 2024 · similarity 0.87)
- StyO: Stylize Your Face in Only One-Shot (AAAI 2025 · similarity 0.87)
- Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles (AAAI 2025 · similarity 0.86)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.86)
- FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models (NeurIPS 2024 · similarity 0.86)
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.
