A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis

ArXi:2402.12760v2 Announce Type: replace-cross Well-designed prompts have nstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model