all AI news
Subject-driven Text-to-Image Generation via Apprenticeship Learning. (arXiv:2304.00186v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Recent text-to-image generation models like DreamBooth have made remarkable
progress in generating highly customized images of a target subject, by
fine-tuning an ``expert model'' for a given subject from a few examples.
However, this process is expensive, since a new expert model must be learned
for each subject. In this paper, we present SuTI, a Subject-driven
Text-to-Image generator that replaces subject-specific fine tuning with
\emph{in-context} learning. Given a few demonstrations of a new subject, SuTI
can instantly generate novel renditions …
arxiv context dreambooth examples expert fine-tuning generator image image generation image generation models image generator images novel optimization paper process progress text text-to-image text-to-image generator