TCIG: Two-Stage Controlled Image Generation with Quality Enhancement through Diffusion

arXiv:2403.01212v1 Announce Type: new
Abstract: In recent years, significant progress has been made in the development of text- to-image generation models. However, these models still face limitations when it comes to achieving full controllability during the generation process. Often, spe- cific training or the use of limited models is required, and even then, they have certain restrictions. To address these challenges, A two-stage method that effec- tively combines controllability and high quality in the generation of images is proposed. This …

abstract arxiv cs.cv development diffusion face image image generation image generation models limitations process progress quality stage text through training type