HappyHorse 1.0 Reference to Video: Multi-Image Subject-to-Video AI Model | RunComfy

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/happyhorse/happyhorse-1-0/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "image_url_1": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png",
    "prompt": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look."
  }'

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": "modelApiDoc_navInputSchema",
  "required": [
    "image_url_1",
    "prompt"
  ],
  "properties": {
    "image_url_1": {
      "title": "Reference Image 1 (character1)",
      "description": "First reference image. Tag this subject in the prompt as character1. Format: JPEG, JPG, PNG, or WEBP. Short side ≥ 400px, recommended 720P or higher, max 10MB.",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png"
    },
    "image_url_2": {
      "title": "Reference Image 2 (character2)",
      "description": "Optional second reference image. Tag this subject in the prompt as character2. Format: JPEG, JPG, PNG, or WEBP. Leave blank to skip.",
      "type": "string"
    },
    "image_url_3": {
      "title": "Reference Image 3 (character3)",
      "description": "Optional third reference image. Tag this subject in the prompt as character3. Format: JPEG, JPG, PNG, or WEBP. Leave blank to skip.",
      "type": "string"
    },
    "image_url_4": {
      "title": "Reference Image 4 (character4)",
      "description": "Optional fourth reference image. Tag this subject in the prompt as character4. Leave blank to skip.",
      "type": "string"
    },
    "image_url_5": {
      "title": "Reference Image 5 (character5)",
      "description": "Optional fifth reference image. Tag this subject in the prompt as character5. Leave blank to skip.",
      "type": "string"
    },
    "image_url_6": {
      "title": "Reference Image 6 (character6)",
      "description": "Optional sixth reference image. Tag this subject in the prompt as character6. Leave blank to skip.",
      "type": "string"
    },
    "image_url_7": {
      "title": "Reference Image 7 (character7)",
      "description": "Optional seventh reference image. Tag this subject in the prompt as character7. Leave blank to skip.",
      "type": "string"
    },
    "image_url_8": {
      "title": "Reference Image 8 (character8)",
      "description": "Optional eighth reference image. Tag this subject in the prompt as character8. Leave blank to skip.",
      "type": "string"
    },
    "image_url_9": {
      "title": "Reference Image 9 (character9)",
      "description": "Optional ninth reference image. Tag this subject in the prompt as character9. Leave blank to skip.",
      "type": "string"
    },
    "prompt": {
      "title": "Prompt",
      "description": "Describe the scene, motion, camera, and lighting. Refer to each reference image with character1, character2, character3 … in the order they appear above. Max 2500 Chinese / 5000 non-Chinese characters.",
      "type": "string",
      "default": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look.",
      "maxLength": 5000
    },
    "aspect_ratio": {
      "title": "Aspect Ratio (W:H)",
      "description": "Output video aspect ratio.",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:3",
        "3:4"
      ],
      "default": "16:9"
    },
    "resolution": {
      "title": "Resolution",
      "description": "Output video resolution. The model supports 720P or 1080P.",
      "type": "string",
      "enum": [
        "720P",
        "1080P"
      ],
      "default": "1080P"
    },
    "duration": {
      "title": "Duration",
      "description": "Output video duration in seconds. Allowed values: 3–15.",
      "type": "integer",
      "enum": [
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "default": 5
    },
    "seed": {
      "title": "Seed",
      "description": "Optional seed for reproducible generations. Use 0 to let the provider randomize.",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647,
      "default": 0
    },
    "watermark": {
      "title": "Watermark",
      "description": "Whether to keep the provider watermark on the generated video.",
      "type": "boolean",
      "default": false
    }
  }
}