CogView3：通过中继扩散实现更精细更快速的文本到图像生成。

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

March 8, 2024

作者: Wendi Zheng, Jiayan Teng, Zhuoyi Yang, Weihan Wang, Jidong Chen, Xiaotao Gu, Yuxiao Dong, Ming Ding, Jie Tang

cs.AI

摘要

最近文本到图像生成系统的进展主要受到扩散模型的推动。然而，单阶段文本到图像扩散模型仍然面临着计算效率和图像细节精炼方面的挑战。为了解决这一问题，我们提出了CogView3，这是一种创新的级联框架，可以提升文本到图像扩散的性能。CogView3是第一个在文本到图像生成领域实现中继扩散的模型，通过首先创建低分辨率图像，然后应用基于中继的超分辨率来执行任务。这种方法不仅产生了具有竞争力的文本到图像输出，而且极大地减少了训练和推断成本。我们的实验结果表明，CogView3在人类评估中比当前最先进的开源文本到图像扩散模型SDXL表现提高了77.0\%，同时仅需要大约1/2的推断时间。CogView3的精简变体在仅利用SDXL推断时间的1/10的情况下实现了可比的性能。

English

Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0\% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.