Research map / Image generation / Text-to-image diffusion
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Liming Jiang, Qing Yan, Yumin Jia, Zichuan Liu, Hao Kang, Xin Lu
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 stage-2 SFT with SPMS synthetic data (multi-stage training) (ablation) | InfU · Portrait benchmark | CLIPScore: 0.292 -> 0.318 | Improved |
| add stage-2 SFT with SPMS synthetic data (multi-stage training) (ablation) | InfU · Portrait benchmark | PickScore: 0.212 -> 0.221 | Improved |
| add stage-2 SFT with SPMS synthetic data (multi-stage training) (ablation) | InfU · Portrait benchmark | ID Loss: 0.172 -> 0.209 | Hurt |
| use SPMS instead of SPSS synthetic data in stage-2 SFT (ablation) | InfU · Portrait benchmark | ID Loss: 0.368 -> 0.209 | Improved |
| use SPMS instead of SPSS synthetic data in stage-2 SFT (ablation) | InfU · Portrait benchmark | CLIPScore: 0.303 -> 0.318 | Improved |
| add IP-Adapter for identity injection with InfuseNet (ablation) | InfU · Portrait benchmark | CLIPScore: 0.318 -> 0.241 | Hurt |
| add IP-Adapter for identity injection with InfuseNet (ablation) | InfU · Portrait benchmark | ID Loss: 0.209 -> 0.180 | Improved |
| use InfU instead of PuLID-FLUX | PuLID-FLUX · Portrait benchmark | ID Loss: 0.225 -> 0.209 | Improved |
| use InfU instead of PuLID-FLUX | PuLID-FLUX · Portrait benchmark | CLIPScore: 0.286 -> 0.318 | Improved |
| use InfU instead of PuLID-FLUX | PuLID-FLUX · User study | best selection rate (%): 27.2% -> 72.8% | Improved |
Closest papers by meaning
- When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (CVPR 2024 · similarity 0.87)
- HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion (CVPR 2025 · similarity 0.85)
- PFStorer: Personalized Face Restoration and Super-Resolution (CVPR 2024 · similarity 0.85)
- FaceMe: Robust Blind Face Restoration with Personal Identification (AAAI 2025 · similarity 0.85)
- PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization (CVPR 2024 · similarity 0.85)
- Diffusion Self-Distillation for Zero-Shot Customized Image Generation (CVPR 2025 · similarity 0.85)
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.
