PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Zinan Guo, Yanze Wu, Zhuowei Chen, Lang Chen, Peng Zhang, Qian He
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper56
- Phantom: Subject-Consistent Video Generation via Cross-Modal AlignmentLijie Liu, Tianxiang Ma, Bingchuan Li, Zhuowei Chen 等ICCV 2025 · 被引用 128 次
- XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT ModulationBowen Chen, Brynn zhao, Haomiao Sun, Li Chen 等NeurIPS 2025 · 被引用 60 次
- VACE: All-in-One Video Creation and EditingZeyinzi Jiang, Zhen Han, Chaojie Mao, Jingfeng Zhang 等ICCV 2025 · 被引用 58 次
- Does FLUX Already Know How to Perform Physically Plausible Image Composition?Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang 等ICLR 2026 · 被引用 34 次
- DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag EditingZihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang 等ICLR 2026 · 被引用 33 次
它引用的顶会 Paper28
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
相关 Paper
- Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion modelsKyungmin Lee, Sangkyung Kwak, Kihyuk Sohn, Jinwoo ShinNeurIPS 2024 · 被引用 13 次
- Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image CustomizationYeji Song, Jimyeong Kim, Wonhark Park, Wonsik Shin 等AAAI 2025 · 被引用 6 次
- Infinite-Story: A Training-Free Consistent Text-to-Image GenerationJihun Park, Kyoungmin Lee, Jongmin Gim, Hyeonseo Jo 等AAAI 2026 · 被引用 1 次
- Customization Assistant for Text-to-image GenerationYufan Zhou, Ruiyi Zhang, Jiuxiang Gu, Tong SunCVPR 2024 · 被引用 10 次
- Semantic Alignment for Pose-Invariant Identity Preserving DiffusionJiwon Kim, Seonhwa Kim, Soobin Park, Eunju Cha 等CVPR 2026
