4 papers · 1 filter
MONKEY: Masking ON KEY-Value Activation Adapter for Personalization
James Baker
Personalizing diffusion models allows users to generate new images that incorporate a given subject, allowing more control than a text prompt. These models often suffer somewhat wh…
Style Ambiguity Loss Using CLIP
James Baker
In this work, we explore using the style ambiguity training objective, originally used to approximate creativity, on a diffusion model. However, this objective requires the use of…
BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion
James Baker
Textual Inversion remains a popular method for personalizing diffusion models, in order to teach models new subjects and styles. We note that textual inversion has been underexplor…
Using Multimodal Foundation Models and Clustering for Improved Style Ambiguity Loss
James Baker
Teaching text-to-image models to be creative involves using style ambiguity loss, which requires a pretrained classifier. In this work, we explore a new form of the style ambiguity…