Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval

TL;DR

This paper tackles the problem of image hallucination in text-to-image diffusion models by retrieving factual images and using editing tools to improve factual accuracy and realism.

Contribution

It introduces a novel method that incorporates external factual image retrieval and editing tools to reduce hallucinations in generated images.

Findings

Improved factual accuracy in generated images.

Effective use of external factual images for editing.

Reduction in hallucination types in text-to-image synthesis.

Abstract

Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accurately reflect the factual information and common sense conveyed by the input text prompts. We refer to this issue as Image hallucination. Drawing from studies on hallucinations in language models, we classify this problem into three types and propose a methodology that uses factual images retrieved from external sources to generate realistic images. Depending on the nature of the hallucination, we employ off-the-shelf image editing tools, either InstructPix2Pix or IP-Adapter, to leverage factual information from the retrieved image. This approach enables the generation of images that accurately reflect the facts and common sense.