Search for: All records

The popularization of Text-to-Image (T2I) diffusion models enables the genera- tion of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that al- lows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text- to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. 

In 2019, all attendees were encouraged to submit their work to the TMS journals Integrating Materials and Manufacturing Innovation and Metallurgical and Materials Transactions A, which will be publishing topical collections on Integrated Computational Materials Engineering (ICME). These collections take the place of a traditional conference proceedings publication. Only submissions from the 5th World Congress on Integrated Computational Materials Engineering (ICME 2019) attendees were considered for these collections. Participants in ICME 2019 have been strongly encouraged to contribute to this effort.