Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a webpage: https://raphael-painter.github.io/.

翻译：文本到图像生成技术近期取得了显著突破。本文提出一种名为RAPHAEL的文本条件图像扩散模型，旨在生成高度艺术化的图像，精准刻画包含多个名词、形容词和动词的文本提示。该模型通过堆叠数十个混合专家（MoE）层（即空间MoE层和时间MoE层），实现了从网络输入到输出的数十亿条扩散路径（路由）。每条路径直观地扮演"画师"角色，在特定扩散时间步中将特定文本概念描绘到指定图像区域。综合实验表明，RAPHAEL在图像质量和美学吸引力上均超越近期顶尖模型（如Stable Diffusion、ERNIE-ViLG 2.0、DeepFloyd和DALL-E 2）。首先，RAPHAEL在跨风格图像切换中表现卓越，涵盖日漫、写实、赛博朋克和水墨插画等多元风格。其次，单个参数规模达30亿的模型，在1,000块A100 GPU上训练两个月后，在COCO数据集上实现了零样本FID值6.61的最优成绩。此外，在ViLG-300基准的人工评估中，RAPHAEL显著优于同类模型。我们相信，RAPHAEL具有推动学术界与工业界图像生成研究前沿的潜力，为该快速演进领域开辟未来突破之路。更多详情请访问网页：https://raphael-painter.github.io/。