all AI news
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm
March 19, 2024, 4:49 a.m. | Yi Wu, Ziqiang Li, Heliang Zheng, Chaoyue Wang, Bin Li
cs.CV updates on arXiv.org arxiv.org
Abstract: Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However, existing methods primarily integrate reference images within the text embedding space, leading to a complex entanglement of image and text information, which poses challenges for preserving both identity fidelity and semantic consistency. To tackle this challenge, we propose Infinite-ID, an ID-semantics decoupling paradigm for identity-preserved personalization. Specifically, …
abstract arxiv cs.cv diffusion diffusion models embedding entanglement however identity image image generation images paradigm personalization progress reference semantics space text text embedding text-to-image type via
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Software Engineer, Generative AI (C++)
@ SoundHound Inc. | Toronto, Canada