> ## Documentation Index > Fetch the complete documentation index at: https://docs.powertokens.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling Image Generation kling-v2-new > Submit a Kling native async image generation or image-to-image task via `/kling/v1/images/generations`. ## OpenAPI ````yaml api-reference/en/zmodelImage/kling/kling-v2-new-image-generations.json POST /kling/v1/images/generations openapi: 3.0.1 info: title: Kling Image Generation Task - Submit Task version: 1.0.0 description: >- Submit a Kling native async image generation or image-to-image task via `/kling/v1/images/generations`. servers: - url: https://api.powertokens.ai description: '' security: [] tags: - name: Kling description: Kling native async task endpoints paths: /kling/v1/images/generations: post: tags: - Kling summary: Kling Image Generation Task description: >- Submit a Kling native async image generation or image-to-image task via `/kling/v1/images/generations`. operationId: createKlingImageGeneration parameters: - name: Content-Type in: header required: true schema: type: string default: application/json description: Data exchange format requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/KlingRequest' examples: request: summary: Request example value: model_name: kling-v2-new prompt: Generate a Pixar-style puppy negative_prompt: '' image: >- https://p1-kling.klingai.com/kcdn/cdn-kcdn112452/kling-qa-test/dog.png 'n': 2 external_task_id: '' callback_url: '' responses: '200': description: Task accepted. content: application/json: schema: $ref: '#/components/schemas/SubmitResponse' security: - bearerAuth: [] components: schemas: KlingRequest: type: object required: - model_name - prompt - image properties: model_name: type: string description: Model name enum: - kling-v2-new prompt: type: string description: |- Positive text prompt Must not exceed 2500 characters. maxLength: 2500 negative_prompt: type: string description: >- Negative text prompt Must not exceed 2500 characters. Note: Negative prompt is not supported in image-to-image mode (i.e., when the image field is not empty). maxLength: 2500 image: type: string description: >- Reference image - Supports image Base64 encoding or image URL (must be accessible) Base64 encoding notes: Please ensure all image data parameters use Base64 encoding format. When using Base64, do not add any prefix such as data:image/png;base64, — provide only the Base64 encoded string itself. Correct example: `iVBORw0KGgoAAAANSUhEUgAAAAUA...` Incorrect example: `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA...` - Supported image formats: .jpg / .jpeg / .png - Image file size must not exceed 10MB, image dimensions must be at least 300px, aspect ratio between 1:2.5 ~ 2.5:1 - Required when image_reference is not empty image_reference: type: string enum: - subject - face description: >- Image reference type. - subject (character feature reference), face (facial appearance reference) - When using face (facial appearance reference), the uploaded image must contain only 1 face element_list: type: array items: type: object required: - element_id properties: element_id: type: integer format: int64 description: Element ID from the element library. description: >- Element reference list, configured based on element IDs in the element library. Use key:value format: `"element_list":[{ "element_id": long },{ "element_id": long }]` The total number of reference elements and reference images must not exceed 10. maxItems: 10 resolution: type: string enum: - 1k default: 1k description: Generated image resolution. 'n': type: integer minimum: 1 maximum: 9 default: 1 description: Number of images to generate. aspect_ratio: type: string description: Aspect ratio of generated images (width:height) default: '16:9' enum: - '1:1' - '16:9' - '4:3' - '3:2' - '2:3' - '3:4' - '9:16' - '21:9' watermark_info: type: object description: |- Whether to also generate a watermarked result. - Defined via the enabled parameter: ```json "watermark_info": { "enabled": boolean } ``` - true to generate, false to not generate - Custom watermarks are not currently supported properties: enabled: type: boolean description: true to generate watermarked result, false to not generate. callback_url: type: string description: >- Callback notification URL for this task. If configured, the server will proactively notify when the task status changes. external_task_id: type: string description: >- Custom task ID. - Does not override the system-generated task ID, but supports querying by this ID. - Must be unique per user. SubmitResponse: type: object properties: code: type: integer description: Error code; see error codes for details. example: 0 message: type: string description: Error message. example: string request_id: type: string description: >- Request ID, system-generated, used for request tracking and troubleshooting. example: string data: type: object properties: task_id: type: string description: Task ID, system-generated. example: string task_info: type: object description: Task creation parameter information. properties: external_task_id: type: string description: Client-provided custom task ID. example: string task_status: type: string description: >- Task status. Enum values: submitted, processing, succeed, failed. enum: - submitted - processing - succeed - failed example: submitted created_at: type: integer format: int64 description: Task creation time, Unix timestamp in milliseconds. example: 1722769557708 updated_at: type: integer format: int64 description: Task update time, Unix timestamp in milliseconds. example: 1722769557708 securitySchemes: bearerAuth: type: http scheme: bearer description: 'Pass `Authorization: Bearer ` in the request header.' ````