Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models

TL;DR

This paper introduces Visually Guided Decoding (VGD), a gradient-free method that uses large language models and CLIP guidance to generate coherent, interpretable prompts for text-to-image models, improving control and relevance.

Contribution

VGD is a novel gradient-free approach that leverages LLMs and CLIP for effective prompt inversion, enhancing interpretability and semantic alignment without additional training.

Findings

VGD outperforms existing prompt inversion methods in coherence and relevance.

VGD improves interpretability and control in text-to-image generation.

VGD does not require additional training, increasing flexibility.

Abstract

Text-to-image generative models like DALL-E and Stable Diffusion have revolutionized visual content creation across various applications, including advertising, personalized media, and design prototyping. However, crafting effective textual prompts to guide these models remains challenging, often requiring extensive trial and error. Existing prompt inversion approaches, such as soft and hard prompt techniques, are not so effective due to the limited interpretability and incoherent prompt generation. To address these issues, we propose Visually Guided Decoding (VGD), a gradient-free approach that leverages large language models (LLMs) and CLIP-based guidance to generate coherent and semantically aligned prompts. In essence, VGD utilizes the robust text generation capabilities of LLMs to produce human-readable prompts. Further, by employing CLIP scores to ensure alignment with user-specified visual concepts, VGD enhances the interpretability, generalization, and flexibility of prompt generation without the need for additional training. Our experiments demonstrate that VGD outperforms existing prompt inversion techniques in generating understandable and contextually relevant prompts, facilitating more intuitive and controllable interactions with text-to-image models.