{
  "schema_version": 1,
  "id": "minimax-h3-image",
  "name": "MiniMax H3 Image",
  "size_multiple": 32,
  "description": "Text-to-image and reference-image editing with the six-step PDD checkpoint. Requires the MiniMax-H3-Image 2D VAE and MiniMax-H3 Qwen3-VL-32B text encoder with its vision tower.",
  "model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3-Image",
  "slots": [
    {
      "id": "diffusion_model",
      "required": true
    },
    {
      "id": "llm",
      "required": true,
      "label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
    },
    {
      "id": "llm_vision",
      "required": false,
      "label": "Vision tower (required when not included in the text encoder)"
    },
    {
      "id": "vae",
      "required": true,
      "label": "MiniMax-H3-Image 2D VAE"
    }
  ],
  "defaults": {
    "sampling_method": "euler",
    "cfg_scale": 1,
    "steps": 6,
    "width": 1024,
    "height": 1024,
    "custom_sigmas": [
      1.0,
      0.9675236940383911,
      0.8875485062599182,
      0.75,
      0.5327739119529724,
      0.23200887441635132,
      0.0
    ]
  },
  "features": [
    "ref_images"
  ]
}