{
  "schema_version": 1,
  "id": "minimax-h3-ref2va",
  "name": "MiniMax H3 Ref2VA",
  "size_multiple": 32,
  "description": "Supply image, video or audio references with compatible Ref2VA weights. Use either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector. Image/video references need the matching vision tower. Audio VAE is optional for silent video.",
  "model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
  "slots": [
    {
      "id": "diffusion_model",
      "required": true
    },
    {
      "id": "llm",
      "required": true,
      "label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
    },
    {
      "id": "llm_vision",
      "required": false,
      "label": "Vision tower (required for image/video references when not included in the text encoder)"
    },
    {
      "id": "embeddings_connectors",
      "required": false,
      "label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
    },
    {
      "id": "vae",
      "required": false,
      "label": "MiniMax H3 Video VAE"
    },
    {
      "id": "tae",
      "required": false
    },
    {
      "id": "audio_vae",
      "required": false,
      "label": "MiniMax H3 Audio VAE"
    }
  ],
  "required_any": [
    [
      "vae",
      "tae"
    ]
  ],
  "video_constraints": {
    "frame_step": 17,
    "frame_offset": 5,
    "frame_rounding": "ceil",
    "min_frames": 5,
    "fixed_fps": 24
  },
  "defaults": {
    "video_frames": 56,
    "fps": 24,
    "cfg_scale": 1,
    "width": 1344,
    "height": 768,
    "sampling_method": "euler"
  },
  "features": [
    "flow_shift",
    "ref_images",
    "ref_videos",
    "ref_audios",
    "ref_video_audios"
  ],
  "disabled_features": [
    "img2img",
    "mask_image"
  ]
}