Abstract
Arbitrary resolution image generation provides a consistent visual experience across devices, having extensive applications for producers and consumers. Current diffusion models increase computational demand quadratically with resolution, causing 4K image generation delays over 100 seconds. To solve this, we explore the second generation upon the latent diffusion models, where the fixed latent generated by diffusion models is regarded as the content representation and we propose to decode arbitrary resolution images with a compact generated latent using a one-step generator. Thus, we present the \textbf{InfGen}, replacing the VAE decoder with the new generator, for generating images at any resolution from a fixed-size latent without retraining the diffusion models, which simplifies the process, reducing computational complexity and can be applied to any model using the same latent space. Experiments show InfGen is capable of improving many models into the arbitrary high-resolution era while cutting 4K image generation time to under 10 seconds.
Abstract (translated)
任意分辨率图像生成为不同设备提供了一致的视觉体验，在生产和消费领域有着广泛的应用。当前的扩散模型（diffusion models）计算需求随着分辨率的增加呈二次增长，导致4K图像生成延迟超过100秒。为了应对这一问题，我们探索了基于潜在扩散模型的第二代技术，其中由扩散模型产生的固定潜在表示被视为内容表示，并且我们提出使用一步式生成器从紧凑的潜在表示中解码任意分辨率的图像。因此，我们提出了**InfGen**方法，通过用新的生成器替换变分自编码器（VAE）解码器，在不重新训练扩散模型的情况下，可以从固定大小的潜在表示生成任何分辨率的图像，简化了流程并减少了计算复杂性，适用于使用相同潜在空间的任何模型。实验表明，InfGen能够将许多模型提升到任意高分辨率时代，并且将4K图像生成时间缩短至10秒以内。
URL
https://arxiv.org/abs/2509.10441
