MiniMax Releases Open-Weight H3-Image Model for 16MP Generation and Editing

MiniMax released MiniMax-H3-Image, an open-weight image generation and editing model that produces roughly 16-megapixel images in about 10 seconds. The model supports text-to-image and image editing with up to 16 reference images, and is available through the MiniMax API, MiniMax Code, and Hailuo AI, with 50% off 16MP+ generations during launch week.
Event version 1.
Key insights
High-resolution output
MiniMax-H3-Image generates images of about 16 megapixels at every aspect ratio, from 4096x4096 to 6272x2688, directly without an upscaler.
Unified generation and editing
Generation and editing are unified in one checkpoint, supporting text-to-image and editing of one or more reference images, with up to 16 reference images.
Fast distilled sampling
The checkpoint is distilled to 6 sampling steps with no classifier-free guidance, and the model produces 4K images in about 10 seconds.
Availability and launch pricing
The model is available via the MiniMax API, MiniMax Code, and Hailuo AI, with 50% off 16MP+ generations during launch week.