按年被提到
20232023 · 2 次2026
视觉、语音与图像生成›扩散模型·arXiv:2309.06380 · cs.LG

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

Xingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng, Qiang Liu · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-09-14 · 最近 2023-10-03
2不同的人
2活跃月份
2讨论串
33被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requiring tens of inference steps to obtain satisfactory results. Previous attempts to improve its sampling speed and reduce computational costs through distillation have been unsuccessful in achieving a functional one-step model. In this paper, we explore a recent method called Rectified Flow, which, thus far, has only been applied to small datasets. The core of Rectified Flow lies in its \emph{reflow} procedure, which straightens the trajectories of probability flows, refines the coupling between noises and images, and facilitates the distillation process with student models. We propose a novel text-conditioned pipeline to turn Stable Diffusion (SD) into an ultra-fast one-step model, in which we find reflow plays a critical role in improving the assignment between noise and images. Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23.3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37.2$ $\rightarrow$ $23.3$ in FID). By utilizing an expanded network with 1.7B parameters, we further improve the FID to $22.4$. We call our one-step models \emph{InstaFlow}. On MS COCO 2014-30k, InstaFlow yields an FID of $13.1$ in just $0.09$ second, the best in $\leq 0.1$ second regime, outperforming the recent StyleGAN-T ($13.9$ in $0.1$ second). Notably, the training of InstaFlow only costs 199 A100 GPU days. Codes and pre-trained models are available at \url{github.com/gnobitab/InstaFlow}.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论gwern · 2023-10

“No, that's easy. We had the equivalent of that in GANs many years ago. If you've never seen GAN editing, here's a quick video: https://www.youtube.com/watch?v=Z1-3JKDh0nI (Background: https://gwern.net/face#reversing-stylegan-to-control-modify-images ) You just classify the latents and then you can edit it. These days, with pretrained models like CLIP, yo…”

Weird A.I. Yankovic, a cursed deep dive into the world of voice cloning原评论 ↗
被提交为 story · 1 次