ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image
  Generation

Junying Chen; Zhenyang Cai; Pengcheng Chen; Shunian Chen; Ke Ji; Xidong Wang; Yunjin Yang; Benyou Wang

返回文献探索

Paper · arXiv 2506.18095

ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

Junying Chen, Zhenyang Cai, Pengcheng Chen, Shunian Chen, Ke Ji, Xidong Wang, Yunjin Yang, Benyou Wang

67 upvotesJune 22, 2025arXiv 预印本

AI 摘要

ShareGPT-4o-Image and Janus-4o enable open research in photorealistic, instruction-aligned image generation through a large dataset and multimodal model.

multimodal generative modelstext-to-imagetext-and-image-to-imagephotorealisticinstruction-aligneddatasetlarge language modelsynthetic samples

Abstract

Recent advances in multimodal generative models have unlocked photorealistic, instruction-aligned image generation, yet leading systems like GPT-4o-Image remain proprietary and inaccessible. To democratize these capabilities, we present ShareGPT-4o-Image, the first dataset comprising 45K text-to-image and 46K text-and-image-to-image data, all synthesized using GPT-4o's image generation capabilities for distilling its advanced image generation abilities. Leveraging this dataset, we develop Janus-4o, a multimodal large language model capable of both text-to-image and text-and-image-to-image generation. Janus-4o not only significantly improves text-to-image generation over its predecessor, Janus-Pro, but also newly supports text-and-image-to-image generation. Notably, it achieves impressive performance in text-and-image-to-image generation from scratch, using only 91K synthetic samples and 6 hours of training on an 8 A800-GPU machine. We hope the release of ShareGPT-4o-Image and Janus-4o will foster open research in photorealistic, instruction-aligned image generation.