inference.minimax.h3.hyper.img2vid.v0

The inference.minimax.h3.hyper.img2vid.v0 job animates a provided keyframe into a video with synchronized stereo audio (24 fps, canvas following the keyframe’s aspect ratio) using the MiniMax H3 (Hailuo-03) model. The hyper tier is an 8-evaluation speed tier in the same latency class as turbo; outputs are equally coherent but not pixel-identical to base, fast or turbo at the same seed.

Upload the keyframe as a job input and reference its filename with first_frame; an optional last_frame pins the closing frame too. Naming is optional: with the fields absent, the first uploaded input is the first frame and a second upload, when present, the last frame:

{
    "type": "inference.minimax.h3.hyper.img2vid.v0",
    "config": {
        "prompt": "the scene comes to life, camera slowly pushing in",
        "first_frame": "input.jpg",
        "duration": 8
    }
}

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 input image already fixes the subject and composition, so use the prompt to describe the motion and change you want from it. The hyper 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.

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).

Schema

{
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "additionalProperties": false,
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "inference.minimax.h3.base.img2vid.v0",
        "inference.minimax.h3.fast.img2vid.v0",
        "inference.minimax.h3.base.img2vid.v1",
        "inference.minimax.h3.fast.img2vid.v1",
        "inference.minimax.h3.turbo.img2vid.v0",
        "inference.minimax.h3.hyper.img2vid.v0",
        "inference.minimax.h3.chili.img2vid.v0"
      ]
    },
    "config": {
      "type": "object",
      "required": [
        "prompt"
      ],
      "additionalProperties": false,
      "properties": {
        "first_frame": {
          "type": "string",
          "format": "filename",
          "example": "first_frame.png",
          "description": "Set the starting frame for the video. Optional: defaults to the first uploaded input."
        },
        "last_frame": {
          "type": "string",
          "format": "filename",
          "example": "last_frame.png",
          "description": "Set the ending frame for the video. Optional: defaults to the second uploaded input, when present."
        },
        "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"
          ],
          "default": "adaptive",
          "description": "The aspect ratio always derives from the input image, so only \"adaptive\" is accepted."
        },
        "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 input image."
        },
        "seed": {
          "type": "integer",
          "minimum": 0,
          "maximum": 2147483647,
          "description": "Seed for reproducible generation. Random when omitted."
        }
      }
    }
  }
}