We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly over six different tasks using these prompts. The resulting Prompt Diffusion model is the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation on the trained tasks and generalizes effectively to new, unseen vision tasks with their respective prompts. Our model also shows compelling text-guided image editing results. Our framework, with code publicly available at https://github.com/Zhendong-Wang/Prompt-Diffusion, aims to facilitate research into in-context learning for computer vision.

翻译：我们提出Prompt Diffusion，这是一个框架，用于在基于扩散的生成模型中实现上下文学习。给定一对任务特定的示例图像，例如深度到/从图像和涂鸦到/从图像，以及文本引导，我们的模型自动理解底层任务，并在新查询图像上根据文本引导执行相同任务。为实现这一点，我们提出了一种视觉-语言提示，能够建模广泛的视觉-语言任务，以及一个以此提示为输入的扩散模型。该扩散模型使用这些提示在六个不同任务上联合训练。由此产生的Prompt Diffusion模型是首个能够进行上下文学习的基于扩散的视觉-语言基础模型。它在训练任务上展示了高质量的上下文生成，并能有效泛化到新的、未见过的视觉任务及相应提示。我们的模型还展示了令人信服的文本引导图像编辑结果。我们的框架代码已公开在https://github.com/Zhendong-Wang/Prompt-Diffusion，旨在促进计算机视觉中上下文学习的研究。