Search-T2I: Internet-Augmented Text-to-Image Generation

ICLR 2026 Conference Submission5816 Authors

Keywords: Internet-augmented generation, text-to-image generation

TL;DR: Search-T2I, the first framework that integrates reference images from the Internet into T2I models, effectively mitigating inaccurate image generation caused by uncertain knowledge in text prompt.

Abstract: Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released in February would struggle to generate a suitable poster for a movie premiering in April, because the character designs and styles are uncertain to the model. To solve this problem, we propose an Internet-Augmented text-to-image generation framework (Search-T2I) to compel T2I models clear about such uncertain knowledge by providing them with reference images. Specifically, an active retrieval module is designed to determine whether a reference image is needed based on the given text prompt; a hierarchical image selection module is introduced to find the most suitable image returned by an image search engine to enhance the T2I model; a self-reflection mechanism is presented to continuously evaluate and refine the generated image to ensure faithful alignment with the text prompt. To evaluate the proposed framework's performance, we collect a dataset named Img-Ref-T2I, where text prompts include three types of uncertain knowledge: (1) known but rare. (2) unknown. (3) ambiguous. Moreover, we carefully craft a complex prompt to guide GPT-4o in making preference evaluation, which has been shown to have an evaluation accuracy similar to that of human preference evaluation. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4o by ∼30\% in human evaluation.

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

Submission Number: 5816