NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe Song
2025Year
9Top-tier citations
Abstract
https://chendaryen.github.io/NitroFusion.github.io Figure 1. Our one-step diffusion pipeline generates vibrant and photorealistic images with exceptional detail in a single inference step, broadening the potential for text-to-image synthesis in applications like real-time interactive systems.
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 420e753d-e4f6-4dce-bc54-1949205aa7b0Cited by top-tier papers9
- Autoregressive Adversarial Post-Training for Real-Time Interactive Video GenerationShanchuan Lin, Ceyuan Yang, Hao He, Jianwen Jiang et al.NeurIPS 2025 · 89 citations
- SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-TrainingJianyi Wang, Shanchuan Lin, Zhijie Lin, Yuxi Ren et al.ICLR 2026 · 51 citations
- Normalized Attention Guidance: Universal Negative Guidance for Diffusion ModelsDar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe SongNeurIPS 2025 · 17 citations
- Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement LearningGuanjie Chen, Shirui Huang, Yifu Sun, Kai Liu et al.CVPR 2026 · 17 citations
- Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft EmbeddingsYuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky KalogeitonICLR 2026 · 4 citations
Builds on24
- 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
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 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
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
Related papers
- Temporal Equilibrium MeanFlow: Bridging the Scale Gap for One-Step GenerationYuanpeng Tu, Yunpeng Chen, Xinyu Zhang, Chao Liao et al.CVPR 2026 · 1 citation
- InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationXingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng et al.ICLR 2024 · 358 citations
- UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANsYanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo HouCVPR 2024
- GenDR: Lighten Generative Detail RestorationYan Wang, Shijie Zhao, Kexin Zhang, Junlin Li et al.ICLR 2026 · 5 citations
- SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score DistillationThuan Hoang Nguyen, Anh TranCVPR 2024 · 20 citations
