MiniMax Releases Open Source MiniMax-H3-Image Model Supporting 16 Million Pixel Image Generation

MiniMax has open-sourced the image generation and editing model MiniMax-H3-Image, which supports text-to-image generation and image editing, allowing up to 16 reference images as input. The model can directly generate images with approximately 16 million pixels, with resolutions ranging from 4096×4096 to 6272×2688, and the sampling steps have been distilled down to 6 steps. The model's diffusion transformer has 33.1 billion parameters, with weights around 68.65GB, and supports deployment on SGLang, vLLM-Omni, diffusers, and ComfyUI. MiniMax claims that the model's instruction-following capability is the strongest among open-source models. The model is now available on the MiniMax API and Conch AI, released under a community license.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.