inference.minimax.h3.fast.ref2vid.v1

The inference.minimax.h3.fast.ref2vid.v1 job generates a video with synchronized stereo audio featuring the identity from reference images (1344×768, 24 fps) using the MiniMax H3 (Hailuo-03) model. The fast tier is the fastest option; outputs are equally coherent but not pixel-identical to base at the same seed.

Upload the references as job inputs and list their filenames in references, in the order the model should read them. Each reference’s role is derived from its blob content type — image/, video/ and audio/* become subject/style, motion, and voice/music references respectively. Up to 9 images, 3 videos and 3 audio files (15 total); audio never on its own. The field itself is optional: with it absent, every uploaded input is a reference, in upload order:

{
    "type": "inference.minimax.h3.fast.ref2vid.v1",
    "config": {
        "prompt": "the subject walks through a sunlit park, birds chirping",
        "references": ["face.jpg", "profile.jpg"],
        "duration": 6
    }
}

Images are JPEG, PNG, WEBP, HEIC or HEIF, 30MB each. Videos are MP4 or MOV with H.264/H.265, 50MB each, 2-15s each and 15s combined, 23.976-60 fps. Audio is WAV or MP3, 15MB each, 2-15s each and 15s combined. Image and video frames must be 256-5760px per side with a width/height ratio between 0.4 and 2.5.

duration, resolution and seed behave as in txt2vid (whole seconds 4–15, rounded up to the 17n+5 frame grid; outputs run 4.46–15.08 s; only the default 768P resolution is valid). The output aspect ratio derives from the first visual reference (snapped to the nearest supported ratio) unless aspect_ratio (one of 16:9, 4:3, 1:1, 3:4, 9:16, 21:9) is set, which overrides it.

Schema

{
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "additionalProperties": false,
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "inference.minimax.h3.base.ref2vid.v0",
        "inference.minimax.h3.fast.ref2vid.v0",
        "inference.minimax.h3.base.ref2vid.v1",
        "inference.minimax.h3.fast.ref2vid.v1"
      ]
    },
    "config": {
      "type": "object",
      "required": [
        "prompt"
      ],
      "additionalProperties": false,
      "properties": {
        "references": {
          "type": "array",
          "minItems": 1,
          "maxItems": 15,
          "items": {
            "type": "string",
            "format": "filename",
            "example": "subject.png",
            "description": "Filename of a reference file."
          },
          "description": "Reference files to feature in the video, in the order the model should read them. The role of each reference is derived from its content type: images, videos, and audio act as subject/style, motion, and voice/music references respectively. Up to 9 images (JPEG, PNG, WEBP, HEIC, or HEIF; 30MB each; 256-5760px per side; width/height ratio 0.4-2.5), 3 videos (MP4 or MOV with H.264/H.265; 50MB each; 2-15s each and 15s combined; same pixel and ratio bounds; 23.976-60 fps), and 3 audio files (WAV or MP3; 15MB each; 2-15s each and 15s combined); audio never on its own. Optional: with the field absent, every uploaded input is a reference, in upload order."
        },
        "prompt": {
          "type": "string",
          "minLength": 3,
          "maxLength": 7000,
          "default": "a dancing cat under moonlight",
          "description": "Description of the desired video and audio."
        },
        "duration": {
          "type": "integer",
          "minimum": 4,
          "maximum": 15,
          "default": 6,
          "description": "Duration of the video in seconds. Rounded up to the model's frame grid (4 s returns 4.46 s, 15 s returns 15.08 s)."
        },
        "aspect_ratio": {
          "type": "string",
          "enum": [
            "adaptive",
            "16:9",
            "4:3",
            "1:1",
            "3:4",
            "9:16",
            "21:9"
          ],
          "default": "adaptive",
          "description": "Controls the approximate aspect ratio of the resulting video. With \"adaptive\" (the default), the aspect ratio derives from the first visual reference (snapped to the nearest supported ratio); an explicit ratio overrides it."
        },
        "resolution": {
          "type": "string",
          "enum": [
            "768P"
          ],
          "default": "768P",
          "description": "Only 768P is supported: the video is generated at a 768px short edge; exact width and height follow the aspect ratio of the first visual reference."
        },
        "seed": {
          "type": "integer",
          "minimum": 0,
          "maximum": 2147483647,
          "description": "Seed for reproducible generation. Random when omitted."
        }
      }
    }
  }
}