Optimizing Prompts for Text-to-Image Generation

Understand

Well-designed prompts can guide text-to-image models to generate amazing images.

• However, the performant prompts are often model-specific and misaligned with user input.
• Instead of laborious human engineering, we propose prompt adaptation, a general framework that automatically adapts original user input to model-preferred prompts.
• Specifically, we first perform supervised fine-tuning with a pretrained language model on a small collection of manually engineered prompts.