Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2023 Workshop on Machine Learning for Creativity and Design

Multi-Subject Personalization

Arushi Jain · Shubham Paliwal · Monika Sharma · Vikram Jamwal · Lovekesh Vig

[ ]
[ Poster
Sat 16 Dec 1:30 p.m. PST — 2:30 p.m. PST


Creative story illustration requires a consistent interplay of multiple characters orobjects. However, conventional text-to-image models face significant challengeswhile producing images featuring multiple personalized subjects. For example, theydistort the subject rendering, or the text descriptions fail to render coherent subjectinteractions. We present Multi-Subject Personalization (MSP) to alleviate someof these challenges. We implement MSP using Stable Diffusion and assess ourapproach against other text-to-image models, showcasing its consistent generationof good-quality images representing intended subjects and interactions.

Chat is not available.