MiniMax H3 Max Reference to video: Мультимодальное видео на Models and API | RunComfy

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/minimax/minimax-h3-max/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Image 1 is the near man; Image 2 is the far man. Keep both faces, hair, and jackets identical to their reference images. Dusk in an empty asphalt parking lot under soft sodium lights. They stand a few meters apart. The near man says flatly: \"So… you actually tried it?\" A beat of wind. The far man answers with a slow half-smile, warm and certain: \"Yeah. I love it.\" The near man exhales and shakes his head once, almost smiling. Static camera, medium wide. Native audio, lip-synced English dialogue, distant traffic hum, wind. No music, no subtitles, no camera movement, no text, no watermark.",
    "prompt_expansion_mode": "balanced",
    "reference_images": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7453/media-files/ref-1.webp",
      "https://playgrounds-storage-public.runcomfy.net/tools/7453/media-files/ref-2.webp"
    ]
  }'

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

{
  "type": "object",
  "title": "Схема входа",
  "required": [
    "prompt",
    "prompt_expansion_mode",
    "reference_images"
  ],
  "properties": {
    "prompt": {
      "title": "Промпт",
      "description": "Describe the scene, motion, camera, and audio. Refer to assets as Image 1, Image 2, Video 1, Audio 1, and say what each reference supplies.",
      "type": "string",
      "default": "Image 1 is the near man; Image 2 is the far man. Keep both faces, hair, and jackets identical to their reference images. Dusk in an empty asphalt parking lot under soft sodium lights. They stand a few meters apart. The near man says flatly: \"So… you actually tried it?\" A beat of wind. The far man answers with a slow half-smile, warm and certain: \"Yeah. I love it.\" The near man exhales and shakes his head once, almost smiling. Static camera, medium wide. Native audio, lip-synced English dialogue, distant traffic hum, wind. No music, no subtitles, no camera movement, no text, no watermark."
    },
    "reference_images": {
      "title": "Референсные изображения",
      "description": "URL-адреса эталонных изображений темы или стиля, указанные в приглашении как «Изображение 1», «Изображение 2» и т. д. В сочетании с видео и аудио максимум 12 справочных файлов.",
      "type": "array",
      "default": [
        "https://playgrounds-storage-public.runcomfy.net/tools/7453/media-files/ref-1.webp",
        "https://playgrounds-storage-public.runcomfy.net/tools/7453/media-files/ref-2.webp"
      ],
      "items": {
        "type": "string",
        "format": "image_uri"
      },
      "maxItems": 12
    },
    "reference_videos": {
      "title": "Референсные видео",
      "description": "Эталонные клипы с движением (около 2–15 секунд каждый; общая продолжительность не более 15 секунд), обозначаемые как Видео 1, Видео 2. В сочетании с изображениями и звуком — не более 12 эталонных файлов.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "video_uri"
      },
      "maxItems": 12
    },
    "reference_audios": {
      "title": "Референсное аудио",
      "description": "Optional voice or ambience clips (about 2-15s each; combined duration at most 15s). Cannot be the only reference; provide at least one image or video with them.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "audio_uri"
      },
      "maxItems": 12
    },
    "aspect_ratio": {
      "title": "Соотношение сторон",
      "description": "Output aspect ratio. adaptive follows the reference framing when possible.",
      "type": "string",
      "enum": [
        "adaptive",
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "default": "adaptive"
    },
    "resolution": {
      "title": "Разрешение",
      "description": "Разрешение родного поколения. 480p быстрее/дешевле; 768p — более резкий вариант по умолчанию.",
      "type": "string",
      "enum": [
        "480p",
        "768p"
      ],
      "default": "768p"
    },
    "duration": {
      "title": "Длительность",
      "description": "Длина создаваемого видео в секундах (5-15).",
      "type": "integer",
      "minimum": 5,
      "maximum": 15,
      "default": 5
    },
    "prompt_expansion_mode": {
      "title": "Режим расширения промпта",
      "description": "Сколько усилий потратить на переписывание подсказки перед генерацией. balanced быстро возвращается; quality тратит больше времени на более насыщенное приглашение.",
      "type": "string",
      "enum": [
        "balanced",
        "quality"
      ],
      "default": "balanced"
    },
    "seed": {
      "title": "Seed",
      "description": "Fixed seed for reproducible results. Use -1 for a random seed.",
      "type": "integer",
      "default": -1
    },
    "enable_safety_checker": {
      "title": "Включить проверку безопасности",
      "description": "Если установлено значение true, проверка безопасности будет включена.",
      "type": "boolean",
      "default": true
    }
  }
}