PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Zinan Guo, Yanze Wu, Zhuowei Chen, Lang Chen, Peng Zhang, Qian He
Abstract
We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss and accurate ID loss, minimizing disruption to the original model and ensuring high ID fidelity. Experiments show that PuLID achieves superior performance in both ID fidelity and editability. Another attractive property of PuLID is that the image elements (e.g., background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible. Codes and models are available at https://github.com/ToTheBeginning/PuLID.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 06b7b837-0490-4b26-aacc-9dd01550bb5fCited by top-tier papers56
- Phantom: Subject-Consistent Video Generation via Cross-Modal AlignmentLijie Liu, Tianxiang Ma, Bingchuan Li, Zhuowei Chen et al.ICCV 2025 · 128 citations
- XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT ModulationBowen Chen, Brynn zhao, Haomiao Sun, Li Chen et al.NeurIPS 2025 · 60 citations
- VACE: All-in-One Video Creation and EditingZeyinzi Jiang, Zhen Han, Chaojie Mao, Jingfeng Zhang et al.ICCV 2025 · 58 citations
- Does FLUX Already Know How to Perform Physically Plausible Image Composition?Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang et al.ICLR 2026 · 34 citations
- DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag EditingZihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang et al.ICLR 2026 · 33 citations
Builds on28
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion modelsKyungmin Lee, Sangkyung Kwak, Kihyuk Sohn, Jinwoo ShinNeurIPS 2024 · 13 citations
- Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image CustomizationYeji Song, Jimyeong Kim, Wonhark Park, Wonsik Shin et al.AAAI 2025 · 6 citations
- Infinite-Story: A Training-Free Consistent Text-to-Image GenerationJihun Park, Kyoungmin Lee, Jongmin Gim, Hyeonseo Jo et al.AAAI 2026 · 1 citation
- Customization Assistant for Text-to-image GenerationYufan Zhou, Ruiyi Zhang, Jiuxiang Gu, Tong SunCVPR 2024 · 10 citations
- Semantic Alignment for Pose-Invariant Identity Preserving DiffusionJiwon Kim, Seonhwa Kim, Soobin Park, Eunju Cha et al.CVPR 2026
