Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation

TL;DR

This paper explores using GPT-k models to streamline prompt editing in text-to-image generation, reducing manual effort and improving efficiency by focusing on modifier adjustments.

Contribution

It introduces a novel approach of leveraging GPT-k for prompt editing in T2I, highlighting its effectiveness in modifier adjustments over subject replacements.

Findings

GPT-k models focus more on inserting modifiers than replacing words.

GPT-k are more effective in adjusting modifiers rather than predicting changes in primary subjects.

Using GPT-k suggestions can reduce remaining edits by 20-30%.

Abstract

The field of text-to-image (T2I) generation has garnered significant attention both within the research community and among everyday users. Despite the advancements of T2I models, a common issue encountered by users is the need for repetitive editing of input prompts in order to receive a satisfactory image, which is time-consuming and labor-intensive. Given the demonstrated text generation power of large-scale language models, such as GPT-k, we investigate the potential of utilizing such models to improve the prompt editing process for T2I generation. We conduct a series of experiments to compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process. We found that GPT-k models focus more on inserting modifiers while humans tend to replace words and phrases, which includes changes to the subject matter. Experimental results show that GPT-k are more effective in adjusting modifiers rather than predicting spontaneous changes in the primary subject matters. Adopting the edit suggested by GPT-k models may reduce the percentage of remaining edits by 20-30%.