> ## Documentation Index > Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a Kling image-to-video task by model > Create a Kling video from a source image with a model-specific route, then retrieve the video by task ID. Send a source image to `POST /image-to-video/{model}` to create a video task. You can add a prompt to describe the motion. The response contains an `id` that you use to retrieve the result. ## Choose a model Put the model ID in the URL. Do not add a model field to the JSON body. | Model ID | Resolution | Duration | Audio | | ----------------- | --------------------- | ---------------------------- | -------------------------------------------- | | `kling-3.0-turbo` | `720p`, `1080p` | Integer from 3 to 15 seconds | Omit `audio` | | `kling-3.0` | `720p`, `1080p`, `4k` | Integer from 3 to 15 seconds | `native` or `off` | | `kling-2.6` | `720p`, `1080p` | 5 or 10 seconds | `native` or `off`; use `1080p` with `native` | | `kling-2.5-turbo` | `720p`, `1080p` | 5 or 10 seconds | Omit `audio` | ## Request parameters Put each input in `contents`. A `prompt` entry uses `text`; a frame entry uses `url`. The first-frame URL must be accessible to the video service. | Field | Type | Required | Description | | -------------------------- | ------- | ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | `model` | string | Yes | Model ID in the URL. Choose an ID from the table above. | | `contents` | array | Yes | Input entries. Include a `first_frame` image; add a `prompt` entry to describe the motion. | | `contents[].type` | string | Yes | `prompt` or `first_frame`. | | `contents[].text` | string | For a `prompt` entry | Text that describes the motion. | | `contents[].url` | string | For a `first_frame` entry | Public image URL for the source image. | | `settings.resolution` | string | No | Output resolution from the selected model's row above. Defaults to `720p`. | | `settings.aspect_ratio` | string | No | Optional aspect ratio hint. Match it to the source image; generated framing may follow the image. The example uses `16:9`. Defaults to `16:9`. | | `settings.duration` | integer | No | Video length in seconds from the selected model's row above. Defaults to `5`. | | `settings.multi_shot` | boolean | No | For `kling-3.0`, set `true` to request multiple shots. Use `false` for the single-shot example. Defaults to `false`. | | `settings.audio` | string | No | For `kling-3.0` or `kling-2.6`, set `native` for generated audio or `off` for no generated audio. Defaults to `off` for those models. | | `options.callback_url` | string | No | Public URL that receives task updates. | | `options.external_task_id` | string | No | Your identifier for matching the task to your application. | | `options.watermark_info` | object | No | Watermark configuration for the output. | The following request animates one source image as a five-second video: ```json theme={null} { "contents": [ { "type": "prompt", "text": "The camera slowly moves closer to the scene." }, { "type": "first_frame", "url": "https://raw.githubusercontent.com/ultralytics/yolov5/402e17ddf820996f51a191cbb798376e1144f069/data/images/zidane.jpg" } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": false } } ``` Replace the image URL with a public URL for your source image when you use a different image. Send this body to `https://api.cometapi.com/image-to-video/kling-3.0-turbo` with your CometAPI API key. The OpenAPI code panel provides Shell, Python, and JavaScript requests with the same body. ## Retrieve the video The create response has this shape: ```json theme={null} { "code": 0, "message": "SUCCEED", "data": { "id": "example-task-id", "status": "submitted" } } ``` Save `data.id`. Use [Get a Kling task](./tasks) with that ID until the task reaches a terminal status. Read the video URL from the task's `outputs` array. ## OpenAPI ````yaml api/openapi/video/kling/model-routes/post-image-to-video.openapi.json POST /image-to-video/{model} openapi: 3.1.0 info: title: Kling image-to-video model route version: 1.0.0 description: Create a Kling video task from a source image, with an optional prompt. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /image-to-video/{model}: post: summary: Create an image-to-video task description: >- Submit a source image with optional motion text, then receive a task ID for retrieving the generated video. operationId: createKlingModelImageToVideoTask parameters: - name: model in: path required: true description: >- Kling model ID. `kling-3.0` supports 4k resolution. The 2.x models accept 5- or 10-second duration. schema: type: string enum: - kling-3.0-turbo - kling-3.0 - kling-2.6 - kling-2.5-turbo default: kling-3.0-turbo example: kling-3.0-turbo requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageToVideoRequest' example: contents: - type: prompt text: The camera slowly moves closer to the scene. - type: first_frame url: >- https://raw.githubusercontent.com/ultralytics/yolov5/402e17ddf820996f51a191cbb798376e1144f069/data/images/zidane.jpg settings: resolution: 720p aspect_ratio: '16:9' duration: 5 multi_shot: false responses: '200': description: >- The task was created. Use `data.id` to retrieve its status and video output. content: application/json: schema: $ref: '#/components/schemas/CreateTaskResponse' example: code: 0 message: SUCCEED data: id: example-task-id status: submitted x-codeSamples: - lang: Shell label: Create task source: | curl https://api.cometapi.com/image-to-video/kling-3.0-turbo \ -X POST \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ --data-raw '{ "contents": [ { "type": "prompt", "text": "The camera slowly moves closer to the scene." }, { "type": "first_frame", "url": "https://raw.githubusercontent.com/ultralytics/yolov5/402e17ddf820996f51a191cbb798376e1144f069/data/images/zidane.jpg" } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": false } }' - lang: Python label: Create task source: | import os import requests response = requests.post( "https://api.cometapi.com/image-to-video/kling-3.0-turbo", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "contents": [ { "type": "prompt", "text": "The camera slowly moves closer to the scene.", }, { "type": "first_frame", "url": "https://raw.githubusercontent.com/ultralytics/yolov5/402e17ddf820996f51a191cbb798376e1144f069/data/images/zidane.jpg", }, ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": False, }, }, ) response.raise_for_status() print(response.json()["data"]["id"]) - lang: JavaScript label: Create task source: | const response = await fetch( "https://api.cometapi.com/image-to-video/kling-3.0-turbo", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ contents: [ { type: "prompt", text: "The camera slowly moves closer to the scene." }, { type: "first_frame", url: "https://raw.githubusercontent.com/ultralytics/yolov5/402e17ddf820996f51a191cbb798376e1144f069/data/images/zidane.jpg", }, ], settings: { resolution: "720p", aspect_ratio: "16:9", duration: 5, multi_shot: false, }, }), }, ); if (!response.ok) throw new Error(`HTTP ${response.status}`); console.log((await response.json()).data.id); components: schemas: ImageToVideoRequest: type: object required: - contents properties: contents: type: array minItems: 1 description: >- Image and text inputs. Include a `first_frame` image. Add a `prompt` entry to describe the motion. contains: type: object required: - type properties: type: const: first_frame description: >- Identifies the source image required for image-to-video generation. minContains: 1 items: type: object required: - type properties: type: type: string enum: - prompt - first_frame description: >- Input role. Use `prompt` for motion text or `first_frame` for the source image. text: type: string description: Motion description for a `prompt` entry. url: type: string format: uri description: Public image URL for a `first_frame` entry. allOf: - if: properties: type: const: prompt description: Identifies an optional motion prompt. then: required: - text else: required: - url additionalProperties: false settings: $ref: '#/components/schemas/VideoSettings' options: $ref: '#/components/schemas/TaskOptions' additionalProperties: false CreateTaskResponse: type: object required: - code - message - data properties: code: oneOf: - type: integer - type: string description: Request result code. `0` or `success` indicates acceptance. message: type: string description: Result message. msg: type: string description: Additional result message when included in the response. data: type: object description: Task identifier and submission status. required: - id - status properties: id: type: string description: Task ID to use in `GET /tasks?task_ids={id}`. status: type: string description: Task status at submission. VideoSettings: type: object description: >- Video generation settings. The model ID determines which resolution, duration, and audio values are accepted. properties: resolution: type: string enum: - 720p - 1080p - 4k default: 720p description: >- Output resolution. `4k` is available with `kling-3.0`; the other listed models accept `720p` or `1080p`. aspect_ratio: type: string default: '16:9' description: >- Optional aspect ratio hint. Match it to the source image; generated framing may follow the image. The example uses `16:9`. duration: type: integer minimum: 3 maximum: 15 default: 5 description: >- Video length in seconds. Use an integer from 3 to 15 for the 3.0 models, or 5 or 10 for the 2.x models. multi_shot: type: boolean default: false description: >- For `kling-3.0`, set `true` to request multiple shots. Use `false` for the single-shot example. audio: type: string enum: - native - 'off' description: >- For `kling-3.0` or `kling-2.6`, use `native` for generated audio or `off` to disable it. The default is `off`. With `kling-2.6`, `native` requires `1080p`. Omit this field for the Turbo models. additionalProperties: false TaskOptions: type: object description: Optional task delivery and tracking settings. properties: callback_url: type: string format: uri description: Public URL that receives task updates. external_task_id: type: string description: >- Your identifier for matching this task to a record in your application. watermark_info: type: object description: Watermark configuration for the generated video. additionalProperties: true additionalProperties: false securitySchemes: bearerAuth: type: http scheme: bearer description: Authenticate with your CometAPI API key. ````