HiDream-I1-Full

HiDream-I1-Full is an open-source text-to-image generative foundation model with 17B parameters. Built using a sparse diffusion transformer, it delivers state-of-the-art image quality across multiple styles (photorealistic, cartoon, artistic, etc.) and boasts best-in-class prompt following as demonstrated by benchmark evaluations such as HPSv2.1, GenEval, and DPG-Bench. The model is commercially friendly and includes a Gradio demo and detailed inference scripts for easy deployment.