Kling Kling Video O3 4k Reference To Video API | Pricing & Docs

kling/kling-video-o3/4K/reference-to-video

Upload up to seven reference images, write a prompt, and Kling Video O3 4k Reference To Video returns a 3-15s cinematic 4K clip with identity consistency, on RunComfy models and HTTP API.

1. Get started

Use RunComfy's API to run kling/kling-video-o3/4K/reference-to-video. For accepted inputs and outputs, see the model's schema.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/kling/kling-video-o3/4K/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
  }'

2. Authentication

Set the YOUR_API_TOKEN environment variable with your API key (manage keys in your Profile) and include it on every request as a Bearer token via the Authorization header: Authorization: Bearer $YOUR_API_TOKEN.

3. API reference

Submit a request

Submit an asynchronous generation job and immediately receive a request_id plus URLs to check status, fetch results, and cancel.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/kling/kling-video-o3/4K/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
  }'

Monitor request status

Fetch the current state for a request_id ("in_queue", "in_progress", "completed", or "cancelled").

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

Retrieve request results

Retrieve the final outputs and metadata for the given request_id; if the job is not complete, the response returns the current state so you can continue polling.

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

Cancel a request

Cancel a queued job by request_id; in-progress jobs cannot be cancelled.

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

4. File inputs

Hosted file (URL)

Provide a publicly reachable HTTPS URL. Ensure the host allows server-side fetches (no login/cookies required) and isn't rate-limited or blocking bots. Recommended limits: images ≤ 50 MB (~4K), videos ≤ 100 MB (~2–5 min @ 720p). Prefer stable or pre-signed URLs for private assets.

5. Schema

Input schema

{
  "type": "object",
  "title": "Input schema",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "title": "Prompt",
      "description": "Describe the scene, characters, action, camera move, and mood you want the 4K clip to render.",
      "type": "string",
      "default": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
    },
    "images": {
      "title": "Reference Images",
      "description": "Public image URLs that lock the subject identity, props, or style. Up to 7 without a reference video, up to 4 when a reference video is also used.",
      "type": "array"
    },
    "aspect_ratio": {
      "title": "Aspect Ratio (W:H)",
      "description": "Output frame ratio. 16:9 for landscape, 9:16 for vertical social, 1:1 for square.",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "default": "16:9"
    },
    "duration": {
      "title": "Duration (seconds)",
      "description": "Length of the generated 4K clip in seconds. Pricing scales linearly with the selected duration.",
      "type": "integer",
      "enum": [
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "default": 5
    },
    "sound": {
      "title": "Generate Sound",
      "description": "When enabled, synthesize matching ambient audio alongside the 4K video. Only available when no reference video is provided. Pricing is unchanged.",
      "type": "boolean",
      "default": false
    },
    "shot_type": {
      "title": "Shot Type",
      "description": "Editing mode. Use intelligent for auto-decided scope, or customize for prompt-driven manual control.",
      "type": "string",
      "enum": [
        "customize",
        "intelligent"
      ],
      "default": "customize"
    },
    "multi_prompt": {
      "title": "Multi Prompt",
      "description": "Additional prompt segments to guide scene transitions and progressions. The sum of durations in multi_prompt must equal to total video duration.",
      "type": "array",
      "items": {
        "prompt": {
          "title": "Prompt",
          "description": "Additional prompt segments to guide scene transitions and progressions.",
          "type": "string",
          "format": "str"
        },
        "duration": {
          "title": "Duration",
          "description": "Duration of the prompt segment in seconds.",
          "type": "integer",
          "format": "int_slider_with_range",
          "minimum": 3,
          "maximum": 15,
          "default": 5
        }
      },
      "maxItems": 20,
      "minItems": 0
    }
  }
}

Output schema

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "single image URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "single video URL"
      },
      "images": {
        "type": "array",
        "description": "multiple image URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "multiple video URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

RunComfy

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

1. Get started

Use RunComfy's API to run kling/kling-video-o3/4K/reference-to-video. For accepted inputs and outputs, see the model's schema.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/kling/kling-video-o3/4K/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
  }'

3. API reference

Submit a request

Submit an asynchronous generation job and immediately receive a request_id plus URLs to check status, fetch results, and cancel.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/kling/kling-video-o3/4K/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
  }'

Monitor request status

Fetch the current state for a request_id ("in_queue", "in_progress", "completed", or "cancelled").

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

Retrieve request results

Retrieve the final outputs and metadata for the given request_id; if the job is not complete, the response returns the current state so you can continue polling.

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

Cancel a request

Cancel a queued job by request_id; in-progress jobs cannot be cancelled.

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

4. File inputs

Hosted file (URL)

5. Schema

Input schema

{
  "type": "object",
  "title": "Input schema",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "title": "Prompt",
      "description": "Describe the scene, characters, action, camera move, and mood you want the 4K clip to render.",
      "type": "string",
      "default": "A young woman in a deep emerald silk gown walks slowly through a sunlit marble corridor, soft golden rim light glancing off her hair, slow tracking shot beside her, shallow depth of field, photoreal 4K detail."
    },
    "images": {
      "title": "Reference Images",
      "description": "Public image URLs that lock the subject identity, props, or style. Up to 7 without a reference video, up to 4 when a reference video is also used.",
      "type": "array"
    },
    "aspect_ratio": {
      "title": "Aspect Ratio (W:H)",
      "description": "Output frame ratio. 16:9 for landscape, 9:16 for vertical social, 1:1 for square.",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "default": "16:9"
    },
    "duration": {
      "title": "Duration (seconds)",
      "description": "Length of the generated 4K clip in seconds. Pricing scales linearly with the selected duration.",
      "type": "integer",
      "enum": [
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "default": 5
    },
    "sound": {
      "title": "Generate Sound",
      "description": "When enabled, synthesize matching ambient audio alongside the 4K video. Only available when no reference video is provided. Pricing is unchanged.",
      "type": "boolean",
      "default": false
    },
    "shot_type": {
      "title": "Shot Type",
      "description": "Editing mode. Use intelligent for auto-decided scope, or customize for prompt-driven manual control.",
      "type": "string",
      "enum": [
        "customize",
        "intelligent"
      ],
      "default": "customize"
    },
    "multi_prompt": {
      "title": "Multi Prompt",
      "description": "Additional prompt segments to guide scene transitions and progressions. The sum of durations in multi_prompt must equal to total video duration.",
      "type": "array",
      "items": {
        "prompt": {
          "title": "Prompt",
          "description": "Additional prompt segments to guide scene transitions and progressions.",
          "type": "string",
          "format": "str"
        },
        "duration": {
          "title": "Duration",
          "description": "Duration of the prompt segment in seconds.",
          "type": "integer",
          "format": "int_slider_with_range",
          "minimum": 3,
          "maximum": 15,
          "default": 5
        }
      },
      "maxItems": 20,
      "minItems": 0
    }
  }
}

Output schema

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "single image URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "single video URL"
      },
      "images": {
        "type": "array",
        "description": "multiple image URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "multiple video URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

Upload up to seven reference images, write a prompt, and Kling Video O3 4k Reference To Video returns a 3-15s cinematic 4K clip with identity consistency, on RunComfy models and HTTP API.

Table of contents

1. Get started

2. Authentication

3. API reference

Submit a request

Monitor request status

Retrieve request results

Cancel a request

4. File inputs

Hosted file (URL)

5. Schema

Input schema

Output schema

Upload up to seven reference images, write a prompt, and Kling Video O3 4k Reference To Video returns a 3-15s cinematic 4K clip with identity consistency, on RunComfy models and HTTP API.

Table of contents

1. Get started

2. Authentication

3. API reference

Submit a request

Monitor request status

Retrieve request results

Cancel a request

4. File inputs

Hosted file (URL)

5. Schema

Input schema

Output schema

Kling Video O3 4k Reference To Video: 4K Reference-Driven Video Generation on Models and API | RunComfy

Upload up to seven reference images, write a prompt, and Kling Video O3 4k Reference To Video returns a 3-15s cinematic 4K clip with identity consistency, on RunComfy models and HTTP API.

Table of contents

1. Get started

2. Authentication

3. API reference

Submit a request

Monitor request status

Retrieve request results

Cancel a request

4. File inputs

Hosted file (URL)

5. Schema

Input schema

Output schema

Kling Video O3 4k Reference To Video: 4K Reference-Driven Video Generation on Models and API | RunComfy

Upload up to seven reference images, write a prompt, and Kling Video O3 4k Reference To Video returns a 3-15s cinematic 4K clip with identity consistency, on RunComfy models and HTTP API.

Table of contents

1. Get started

2. Authentication

3. API reference

Submit a request

Monitor request status

Retrieve request results

Cancel a request

4. File inputs

Hosted file (URL)

5. Schema

Input schema

Output schema