Dynamic Prompt Optimizing for Text-to-Image Generation
This work addresses the need for automated prompt optimization in text-to-image models, offering a solution to reduce manual intervention for users, though it is incremental as it builds on existing fine-control prompt techniques.
The paper tackles the problem of manual refinement in text-to-image generation by introducing Prompt Auto-Editing (PAE), which uses online reinforcement learning to dynamically optimize word weights and injection time steps, resulting in improved aesthetic scores and semantic consistency in generated images.
Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts. Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images. However, the success of fine-control prompts depends on the accuracy of the text prompts and the careful selection of weights and time steps, which requires significant manual intervention. To address this, we introduce the \textbf{P}rompt \textbf{A}uto-\textbf{E}diting (PAE) method. Besides refining the original prompts for image generation, we further employ an online reinforcement learning strategy to explore the weights and injection time steps of each word, leading to the dynamic fine-control prompts. The reward function during training encourages the model to consider aesthetic score, semantic consistency, and user preferences. Experimental results demonstrate that our proposed method effectively improves the original prompts, generating visually more appealing images while maintaining semantic alignment. Code is available at https://github.com/Mowenyii/PAE.