Feb. 28, 2024, 5:46 a.m. | Daiqing Li, Aleks Kamko, Ehsan Akhgari, Ali Sabet, Linmiao Xu, Suhail Doshi

cs.CV updates on arXiv.org arxiv.org

arXiv:2402.17245v1 Announce Type: new
Abstract: In this work, we share three insights for achieving state-of-the-art aesthetic quality in text-to-image generative models. We focus on three critical aspects for model improvement: enhancing color and contrast, improving generation across multiple aspect ratios, and improving human-centric fine details. First, we delve into the significance of the noise schedule in training a diffusion model, demonstrating its profound impact on realism and visual fidelity. Second, we address the challenge of accommodating various aspect ratios in …

abstract art arxiv color contrast cs.ai cs.cv focus generative generative models human human-centric image image generation improvement insights multiple playground quality state text text-to-image type work

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

Risk Management - Machine Learning and Model Delivery Services, Product Associate - Senior Associate-

@ JPMorgan Chase & Co. | Wilmington, DE, United States

Senior ML Engineer (Speech/ASR)

@ ObserveAI | Bengaluru