HiDream-I1 is an open-source image generation foundation model with 17 billion parameters. It is designed to produce high-quality images from text prompts while keeping inference practical through efficient model design. The project provides full, dev, and fast model variants with different inference step counts. It supports direct Python inference scripts, an interactive Gradio demo, and integration through the Hugging Face Diffusers library. The model uses a Llama 3.1 text encoder path and requires the proper Hugging Face access setup for automatic downloads. It is useful for researchers, developers, and creative AI builders who want an open text-to-image model with strong benchmark performance and multiple deployment options.

Features

  • 17B-parameter image generation model
  • Full, Dev, and Fast variants
  • Text-to-image inference scripts
  • Interactive Gradio demo
  • Hugging Face Diffusers support
  • MIT-licensed code and model release

Project Samples

Project Activity

See All Activity >