SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Jierun Chen, Dongting Hu, Xijie Huang, Huseyin Coskun, Arpit Sahni, Aarush Gupta, Anujraaj Goyal, Dishani Lahiri, Rajesh Singh, Yerlan Idelbayev, Junli Cao, Yanyu Li
Abstract
3 HKUST 4 MBZUAI * Equal contribution † Equal advising Project Page: https://snap-research.github.io/snapgen "…, young sudanese female, glamour, natural, front view, extreme detailed and texture skin, …" "a dolphin in an astronaut suit, Animals, Simple Detail" "an old raccoon wearing a top hat and holding an apple, oil painting in the style of van gogh, …" "… llama wearing sunglasses standing on the deck of a spaceship with the Earth in the background, …"
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 22d3f8ea-d46b-44b4-b7e7-bc3be9a25ebfCited by top-tier papers10
- PocketSR: The Super-Resolution Expert in Your Pocket MobilesHaoze Sun, Linfeng Jiang, Fan Li, Renjing Pei et al.NeurIPS 2025 · 8 citations
- SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency DistillationJunsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu et al.ICCV 2025 · 6 citations
- HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion ModelsYoung D. Kwon, Rui Li, Sijia Li, Da Li et al.AAAI 2026 · 5 citations
- Mobile-VTON: High-Fidelity On-Device Virtual Try-OnZhenchen Wan, Ce Chen, Runqi Lin, Jiaxin Huang et al.CVPR 2026 · 4 citations
- NanoSD: Edge Efficient Foundation Model for Real Time Image RestorationSubhajit Sanyal, Srinivas Soumitri Miriyala, Akshay Janardan Bankar, Manjunath Arveti et al.CVPR 2026 · 3 citations
Builds on35
- 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
- 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
- Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
Related papers
- Guided Score identity Distillation for Data-Free One-Step Text-to-Image GenerationMingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai HuangICLR 2025
- Multi-Concept Customization of Text-to-Image DiffusionNupur Kumari, Bingliang Zhang, Richard Zhang, Eli Shechtman et al.CVPR 2023
- Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion ModelsAndreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn et al.CVPR 2023
- CapHuman: Capture Your Moments in Parallel UniversesChao Liang, Fan Ma, Linchao Zhu, Yingying Deng et al.CVPR 2024
- ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit AdaptationDar-Yen Chen, Hamish Tennent, Ching-Wen HsuCVPR 2024
