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

Donghoon Kim, Minji Bae, Kyuhong Shim, Byonghyo Shim

Keywords: text-to-image, inversion, gradient free hard prompt inversion, language model guidance on latent diffusion model

TL;DR: Visually Guided Decoding (VGD) improves prompt generation for text-to-image models by using language models and CLIP guidance to create coherent, human-readable prompts aligned with visual concepts.

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.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1743