← Search

Zhengyuan Yang*

1 accepted papers

2024

Idea2Img: Iterative Self-Refinement with GPT-4V for Automatic Image Design and Generation

ECCV 2024poster

"We introduce “Idea to Image,”1 an agent system that enables multimodal iterative self-refinement with for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models via iterative explorations. This enables them to efficiently conve…