inference.minimax.h3.ref2vid.v1

The inference.minimax.h3.ref2vid.v1 job generates a video based on the text prompt and the reference files provided using the MiniMax H3 (Hailuo-03) model.

Reference files are listed by filename in references. The role of each reference is implicit in the content type of the file: images become reference_image, videos become reference_video, and audio files become reference_audio. Up to 9 images, 3 videos, and 3 audio files are supported, and audio references require at least one image or video reference:

{
    "type": "inference.minimax.h3.ref2vid.v1",
    "config": {
        "prompt": "the subject walking through a neon city",
        "references": ["subject.png"],
        "duration": 6
    }
}

The output aspect ratio is always adaptive (derived from the input media).

Content moderation is enabled by default and filters NSFW content. Set content_moderation to false to disable it.

Schema

{
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "additionalProperties": false,
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "inference.minimax.h3.ref2vid.v1"
      ]
    },
    "config": {
      "type": "object",
      "required": [
        "prompt",
        "references"
      ],
      "additionalProperties": false,
      "properties": {
        "references": {
          "type": "array",
          "minItems": 1,
          "maxItems": 12,
          "items": {
            "type": "string",
            "format": "filename",
            "example": "subject.png",
            "description": "Filename of a reference file."
          },
          "description": "Reference files to feature in the video. The role of each reference is derived from its content type: images, videos, and audio become reference_image, reference_video, and reference_audio respectively. Up to 9 images, 3 videos, and 3 audio files are supported."
        },
        "prompt": {
          "type": "string",
          "minLength": 3,
          "maxLength": 7000,
          "default": "a dancing cat under moonlight",
          "description": "Description of desired output."
        },
        "content_moderation": {
          "type": "boolean",
          "default": true,
          "description": "Filter NSFW content using MiniMax's content moderation."
        },
        "resolution": {
          "type": "string",
          "enum": [
            "768P",
            "2K"
          ],
          "default": "768P",
          "description": "This controls the general quality level of the output. Exact width and height will vary depending on the aspect ratio of the input image."
        },
        "duration": {
          "type": "integer",
          "minimum": 4,
          "maximum": 15,
          "default": 6,
          "description": "Duration of the video in seconds."
        }
      }
    }
  }
}