Research map / Image generation / Text-to-image diffusion
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm
Yi Wu, Ziqiang Li, Heliang Zheng, Chaoyue Wang, Bin Li
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 identity-enhanced training (no text input, text cross-attention deactivated) (ablation) | Infinite-ID · Raw photo generation | M_FaceNet: 0.593 -> 0.689 | Improved |
| add identity-enhanced training (ablation) | Infinite-ID · Raw photo generation | CLIP-T: 0.329 -> 0.340 | Improved |
| add mixed attention module (ablation) | Infinite-ID · Raw photo generation | CLIP-T: 0.331 -> 0.340 | Improved |
| add mixed attention module (ablation) | Infinite-ID · Raw photo generation | M_FaceNet: 0.700 -> 0.689 | Hurt |
| use mixed attention instead of mutual self-attention (ablation) | Infinite-ID · Raw photo generation | M_FaceNet: 0.398 -> 0.689 | Improved |
| add cross-attention merge of text features (ablation) | Infinite-ID · Raw photo generation | CLIP-T: 0.335 -> 0.340 | Improved |
| use AdaIN-mean instead of no style alignment (ablation) | Infinite-ID · Style image generation | style consistency (qualitative) | Improved |
| use AdaIN-mean instead of standard AdaIN (ablation) | Infinite-ID · Style image generation | ID fidelity (qualitative) | Improved |
| lower the resolution of the input ID image (ablation) | Infinite-ID · Input ID resolution | identity fidelity | No clear effect |
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.
- PhotoMaker — PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding (CVPR 2024) · better on 2 of 3 shared results
- FastComposer — FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention (IJCV 2024) · better on 3 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
- When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (CVPR 2024 · similarity 0.90)
- FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network (AAAI 2025 · similarity 0.89)
- PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding (CVPR 2024 · similarity 0.88)
- InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning (CVPR 2024 · similarity 0.87)
- Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models (NeurIPS 2024 · similarity 0.87)
- ID-Patch: Robust ID Association for Group Photo Personalization (CVPR 2025 · 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.
