In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects.

Despite these strides, evaluating these models poses substantial challenges.

Building an open-domain conversational agent is a challenging problem.

Neural Information Processing Systems http://nips.cc/

Subject-driven image generation is related to text-driven image editing but often needs to perform more sophisticated transformations to source images (e.g., rotating the view, zooming in/out, changing the pose of

We collected about 30 million text-image pairs from multiple channels, and built a 2.5TB new dataset (after tokenization, the size becomes about 250GB). The sources of data are basically classified into the following categories: (1) Professional image websites (both English and Chinese). The images in the websites are usually with captions. We have already introduced tokenizers in section 2.2, and here are some details. Colored grids are all the tokens attended to by the token marked "O".