arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.06807cs.LGcs.CVstat.ML
收藏

多步一致性模型

Multistep Consistency Models

Google DeepMind(谷歌DeepMind)

Jonathan Heek, Emiel Hoogeboom, Tim Salimans

AI总结:

本文提出多步一致性模型,统一一致性模型与扩散模型,通过2至8步采样在训练难度、采样速度与生成质量之间取得平衡,并在图像生成和文本到图像任务上取得优异结果。

摘要:

扩散模型相对容易训练,但生成样本需要许多步骤。一致性模型则难以训练得多,但能在单步内生成样本。在本文中,我们提出多步一致性模型:这是对一致性模型(Song等人,2023)与TRACT(Berthelot等人,2023)的统一,可以在一致性模型与扩散模型之间进行插值,从而在采样速度与采样质量之间进行权衡。具体而言,1步一致性模型就是传统的一致性模型,而$\infty$步一致性模型则是扩散模型。多步一致性模型在实践中表现非常出色。通过将采样预算从单步增加到2至8步,我们可以更容易地训练出生成更高质量样本的模型,同时保留大部分采样速度优势。值得注意的结果包括:在一致性蒸馏下,使用不含对抗训练的简单损失,在Imagenet 64上8步达到1.4 FID,在Imagenet128上8步达到2.1 FID。我们还表明,该方法可扩展到文本到图像的扩散模型,生成的样本质量接近原始模型。

英文摘要:

Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step. In this paper we propose Multistep Consistency Models: A unification between Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that can interpolate between a consistency model and a diffusion model: a trade-off between sampling speed and sampling quality. Specifically, a 1-step consistency model is a conventional consistency model whereas a $\infty$-step consistency model is a diffusion model. Multistep Consistency Models work really well in practice. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1 FID on Imagenet128 in 8 steps with consistency distillation, using simple losses without adversarial training. We also show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑