GLoD: Composing Global Contexts and Local Details in Image Generation

arXiv:2404.15447v1 Announce Type: new
Abstract: Diffusion models have demonstrated their capability to synthesize high-quality and diverse images from textual prompts. However, simultaneous control over both global contexts (e.g., object layouts and interactions) and local details (e.g., colors and emotions) still remains a significant challenge. The models often fail to understand complex descriptions involving multiple objects and reflect specified visual attributes to wrong targets or ignore them. This paper presents Global-Local Diffusion (\textit{GLoD}), a novel framework which allows simultaneous control over …

abstract arxiv capability challenge colors control cs.ai cs.cv diffusion diffusion models diverse emotions global however image image generation images interactions object prompts quality textual type