PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space

ArXi:2604.06061v1 Announce Type: new Text-to-image generation has progressed rapidly, but faithfully generating complex scenes requires extensive trial-and-error to find the exact prompt. In the prompt inversion task, the goal is to recover a textual prompt that can faithfully reconstruct a given target image. Currently, existing methods frequently yield suboptimal reconstructions and produce unnatural, hard-to-interpret prompts that hinder transparency and controllability.