In-Context Learning Unlocked for Diffusion Models

Published: 21 Sept 2023, Last Modified: 23 Dec 2023NeurIPS 2023 spotlightEveryoneRevisionsBibTeX
Keywords: diffusion models, in-context learning
TL;DR: Unlock the in-context learning ability of diffusion models with vision-language prompt.
Abstract: 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 on six different tasks using these prompts. The resulting Prompt Diffusion model becomes the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation for the trained tasks and effectively generalizes to new, unseen vision tasks using their respective prompts. Our model also shows compelling text-guided image editing results. Our framework aims to facilitate research into in-context learning for computer vision. We share our code and pre-trained models at
Supplementary Material: zip
Submission Number: 5631