HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

Azusa, Pengyang Ling, yujie, Pan Zhang, Tong Wu, Xiaoyi Dong, Yuhang Zang, Cao Yuhang, Dahua Lin, Jiaqi Wang

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance: 13 upvotes on Hugging Face Daily Papers, #10 of 18 papers on 2025-04-09. Day-by-day upvote history.

Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution image synthesis presents formidable challenges due to the scarcity and complexity of high-resolution content. To this end, we present HiFlow, a training-free and model-agnostic framework to unlock the resolution potential of pre-trained flow models. Specifically, HiFlow establishes a virtual reference flow within the high-resolution space that effectively captures the characteristics of low-resolution flow information, offering guidance for high-resolution generation through three key aspects: initialization alignment for low-frequency consistency, direction alignment for structure preservation, and acceleration alignment for detail fidelity. By leveraging this flow-aligned guidance, HiFlow substantially elevates the quality of high-resolution image synthesis of T2I models and demonstrates versatility across their personalized variants. Extensive experiments validate HiFlow's superiority in achieving superior high-resolution image quality over current state-of-the-art methods.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.