Skip to main content
Video models

MiniMax H3 — Image to video API

Image to video with MiniMax H3: request parameters, examples and response handling.

← MiniMax H3

Endpoint: POST https://api.higgsfield.ai/minimax/h3/image-to-video

Endpoint ID: minimax/h3/image-to-video

▶Open API PlaygroundMiniMax H3 · Image to video↗

#Usage notes

  • Resolution is fixed to the case-sensitive schema value "2K". The prompt must contain non-whitespace text; the current provider serializer uses only its first 7,000 characters.
  • The output aspect ratio follows the input keyframe even when aspect_ratio is supplied. end_image_url is an optional last frame.

#Quick start

Replace the example media URLs with publicly accessible URLs for your own files before submitting.

cURL
curl --request POST \
  --url https://api.higgsfield.ai/minimax/h3/image-to-video \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --header "Idempotency-Key: ${IDEMPOTENCY_KEY}" \
  --data '{
  "prompt": "A cinematic wide shot of ocean waves at sunset, with gentle camera movement.",
  "image_url": "https://example.com/input.jpg"
}'

#Input schema

prompt string required

Write your prompt here Minimum characters: 1.

duration integer (default: 5)

Requested output duration in seconds. Minimum: 5. Maximum: 15.

image_url string required

Public URL of the input image. Format: uri.

resolution string (default: 2K)

Output resolution tier. Allowed values: "2K".

aspect_ratio string (default: auto)

Output width-to-height ratio. Allowed values: "auto", "adaptive", "21:9", "16:9", "4:3", "1:1", "3:4", "9:16".

end_image_url string

Format: uri.

aigc_watermark boolean (default: false)

See the complete JSON schema below.

Complete JSON schema
json
{
  "type": "object",
  "title": "MiniMax H3 Image to Video Playground",
  "required": [
    "prompt",
    "image_url"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "minLength": 1,
      "description": "Write your prompt here"
    },
    "duration": {
      "type": "integer",
      "title": "Duration",
      "default": 5,
      "maximum": 15,
      "minimum": 5
    },
    "image_url": {
      "type": "string",
      "title": "First frame URL",
      "format": "uri"
    },
    "resolution": {
      "enum": [
        "2K"
      ],
      "type": "string",
      "title": "Resolution",
      "default": "2K"
    },
    "aspect_ratio": {
      "enum": [
        "auto",
        "adaptive",
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "type": "string",
      "title": "Aspect ratio",
      "default": "auto"
    },
    "end_image_url": {
      "type": "string",
      "title": "Last frame URL",
      "format": "uri"
    },
    "aigc_watermark": {
      "type": "boolean",
      "title": "AIGC watermark",
      "default": false
    }
  },
  "additionalProperties": false
}

#Response

Submission returns a request handle. Poll status_url until status is completed, or use webhooks.

Accepted
{
  "status": "queued",
  "request_id": "REQUEST_ID",
  "status_url": "https://api.higgsfield.ai/requests/REQUEST_ID/status",
  "cancel_url": "https://api.higgsfield.ai/requests/REQUEST_ID/cancel"
}

A completed response includes the following output fields:

json
{
  "status": "completed",
  "request_id": "REQUEST_ID",
  "video": {
    "url": "https://example.com/output.mp4"
  }
}

See idempotent requests, polling, request errors and authentication for shared request handling.

Was this page helpful?
Navigation