RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

TL;DR

RealGen is a novel framework that enhances photorealistic text-to-image generation by integrating detector-guided rewards and prompt optimization, significantly improving image realism and detail over existing models.

Contribution

The paper introduces RealGen, combining a detector-guided reward mechanism with diffusion models and prompt optimization to achieve superior photorealism in text-to-image synthesis.

Findings

RealGen outperforms GPT-Image-1 and Qwen-Image in realism and detail.

The Detector Reward effectively quantifies and reduces artifacts.

RealBench provides a human-free, accurate photorealism evaluation.

Abstract

With the continuous advancement of image generation technology, advanced models such as GPT-Image-1 and Qwen-Image have achieved remarkable text-to-image consistency and world knowledge However, these models still fall short in photorealistic image generation. Even on simple T2I tasks, they tend to produce " fake" images with distinct AI artifacts, often characterized by "overly smooth skin" and "oily facial sheens". To recapture the original goal of "indistinguishable-from-reality" generation, we propose RealGen, a photorealistic text-to-image framework. RealGen integrates an LLM component for prompt optimization and a diffusion model for realistic image generation. Inspired by adversarial generation, RealGen introduces a "Detector Reward" mechanism, which quantifies artifacts and assesses realism using both semantic-level and feature-level synthetic image detectors. We leverage this reward signal with the GRPO algorithm to optimize the entire generation pipeline, significantly enhancing image realism and detail. Furthermore, we propose RealBench, an automated evaluation benchmark employing Detector-Scoring and Arena-Scoring. It enables human-free photorealism assessment, yielding results that are more accurate and aligned with real user experience. Experiments demonstrate that RealGen significantly outperforms general models like GPT-Image-1 and Qwen-Image, as well as specialized photorealistic models like FLUX-Krea, in terms of realism, detail, and aesthetics. The code is available at https://github.com/yejy53/RealGen.