CosmicMan: A Text-to-Image Foundation Model for Humans
Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, Wayne Wu
Abstract
We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions. At the heart of CosmicMan's success are the new reflections and perspectives on data and models: (1) We found that data quality and a scalable data production flow are essential for the final results from trained models. Hence, we
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 fb6c1448-405a-4311-971e-d53c2d715cd8Cited by top-tier papers18
- MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank ExpertsJie Zhu, Yixiong Chen, Mingyu Ding, Ping Luo et al.NeurIPS 2024 · 17 citations
- Where Culture Fades: Revealing the Cultural Gap in Text-to-Image GenerationChuancheng Shi, Shangze Li, Shiming Guo, Simiao Xie et al.CVPR 2026 · 14 citations
- PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-Aware MaskJeongho Kim, Hoiyeong Jin, Sunghyun Park, Jaegul ChooICCV 2025 · 6 citations
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human DataWentao Wang, Hang Ye, Fangzhou Hong, Xue Yang et al.NeurIPS 2025 · 6 citations
- GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion TransformersYuxuan Xue, Ruofan Liang, Egor Zakharov, Timur M. Bagautdinov et al.CVPR 2026 · 4 citations
Builds on32
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 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
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
Related papers
- HyperHuman: Hyper-Realistic Human Generation with Latent Structural DiffusionXian Liu, Jian Ren, Aliaksandr Siarohin, Ivan Skorokhodov et al.ICLR 2024 · 81 citations
- Visual Persona: Foundation Model for Full-Body Human CustomizationJisu Nam, Soowon Son, Zhan Xu, Jing Shi et al.CVPR 2025
- LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image GenerationLeigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie et al.ACM MM 2023 · 91 citations
- SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image GenerationPaul Grimal, Michaël Soumm, Hervé Le Borgne, Olivier Ferret et al.AAAI 2026 · 1 citation
- Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction ScenesWenxuan Peng, Bharath Hariharan, Hadar Averbuch-ElorSIGGRAPH 2026
