YaART: Yet Another ART Rendering Technology

arXiv:2404.05666v1 Announce Type: new
Abstract: In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF). During the development of YaART, we especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before. In …

abstract art arxiv cs.cv development diffusion diffusion model feedback fidelity generative generative models human human feedback image image diffusion novel production reinforcement reinforcement learning rendering rlhf study systems technology text text-to-image type