LCM-Lookahead for Encoder-based Text-to-Image Personalization

arXiv:2404.03620v1 Announce Type: new
Abstract: Recent advancements in diffusion models have introduced fast sampling methods that can effectively produce high-quality images in just one or a few denoising steps. Interestingly, when these are distilled from existing diffusion models, they often maintain alignment with the original model, retaining similar outputs for similar prompts and seeds. These properties present opportunities to leverage fast sampling methods as a shortcut-mechanism, using them to create a preview of denoised outputs through which we can backpropagate …

abstract alignment arxiv cs.cv cs.gr denoising diffusion diffusion models encoder image images personalization prompts quality sampling text text-to-image type