Note: All model files below must be downloaded via the LM Downloader client. If you do not have the client, Download >>>
MiniMax-H3-Image is a state-of-the-art open-source model for image generation and editing from the MiniMax H3 family. It combines intelligent understanding of creative intent with the ability to build visual worlds: with precise instruction following, it develops a creative concept into concrete characters, scenes and atmosphere. Generation and editing are unified in one checkpoint, which generates images from text (text-to-image) and edits one or more reference images (image editing), giving creators and developers a flexible and controllable way to create images. It generates images of about 16 megapixels at every aspect ratio, from 4096x4096 (1:1) to 6272x2688 (21:9), directly and without an upscaler. The checkpoint is distilled to 6 sampling steps (6 NFEs) with no classifier-free guidance. Its diffusion transformer (DiT) has the H3 architecture without the audio layers, and it uses the MiniMax-H3 text encoder unchanged.
| Name | Size | Target Dir |
|---|---|---|
| minimax_h3_image_pruned_w4a8.safetensors | 12.55 GB | diffusion_models |
| minimax_h3_image_pruned_int8_convrot.safetensors | 20.98 GB | diffusion_models |
| minimax_h3_image_pruned_bf16.safetensors | 40.23 GB | diffusion_models |