PromptCrafter: Crafting Text-to-Image Prompt through Mixed-Initiative Dialogue with LLM
This addresses the challenge for users of text-to-image models in crafting effective prompts, though it appears incremental as a workshop paper discussing design and future plans.
The paper tackles the problem of helping users efficiently explore text-to-image model capabilities and create effective prompts by introducing PromptCrafter, a mixed-initiative system that enables step-by-step prompt crafting through iterative dialogue with an LLM, resulting in support for intent clarification and prompt refinement.
Text-to-image generation model is able to generate images across a diverse range of subjects and styles based on a single prompt. Recent works have proposed a variety of interaction methods that help users understand the capabilities of models and utilize them. However, how to support users to efficiently explore the model's capability and to create effective prompts are still open-ended research questions. In this paper, we present PromptCrafter, a novel mixed-initiative system that allows step-by-step crafting of text-to-image prompt. Through the iterative process, users can efficiently explore the model's capability, and clarify their intent. PromptCrafter also supports users to refine prompts by answering various responses to clarifying questions generated by a Large Language Model. Lastly, users can revert to a desired step by reviewing the work history. In this workshop paper, we discuss the design process of PromptCrafter and our plans for follow-up studies.