inference.minimax.h3.turbo.ref2vid.v0

The inference.minimax.h3.turbo.ref2vid.v0 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 turbo tier is the fastest option; outputs are equally coherent but not pixel-identical to base or fast 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.turbo.ref2vid.v0",
    "config": {
        "prompt": "the subject walks through a sunlit park, birds chirping",
        "references": ["face.jpg", "profile.jpg"],
        "duration": 6
    }
}

Prompting

The prompt is used exactly as written: nothing rewrites or expands it before it reaches the model, which was trained on descriptive captions. Describe the shot rather than making a request: the subject, setting, time of day, weather, lighting, camera move and motion. For example, “show me what christmas would be like in Tokyo” tends to produce a generic winter scene, while “Shibuya crossing in Tokyo on Christmas Eve at night, light snow falling, crowds with umbrellas, a giant illuminated Christmas tree, neon signs reflecting in the wet street, slow cinematic dolly shot” produces the intended scene. The references already fix who or what appears, so use the prompt to describe the setting, action, motion and camera move you want for them. The turbo tier is a distilled 8-evaluation recipe, so it follows the prompt less closely than base and fast; vague prompts steer it even less, so a detailed description matters more here.

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",
        "inference.minimax.h3.turbo.ref2vid.v0",
        "inference.minimax.h3.hyper.ref2vid.v0",
        "inference.minimax.h3.chili.ref2vid.v0"
      ]
    },
    "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 canvas targets a 768px short edge with a 768x1344 pixel area cap and 32px rounding; 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."
        }
      }
    }
  }
}