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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Donghoon, Bae, Minji, Shim, Kyuhong, Shim, Byonghyo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913949294788608
author Kim, Donghoon
Bae, Minji
Shim, Kyuhong
Shim, Byonghyo
author_facet Kim, Donghoon
Bae, Minji
Shim, Kyuhong
Shim, Byonghyo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08622
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
Kim, Donghoon
Bae, Minji
Shim, Kyuhong
Shim, Byonghyo
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
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.
title Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.08622