> ## 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. # Tạo hình ảnh với Kling > Tạo hình ảnh với Kling qua CometAPI: POST /kling/v1/images/generations hỗ trợ tạo hình ảnh từ prompt và tạo hình ảnh bằng ảnh tham chiếu. ## Tạo hình ảnh Để xem tài liệu tham khảo tham số đầy đủ, hãy xem [tài liệu Kling chính thức](https://kling.ai/document-api/api/image/3-0-omni/image-generation). Sử dụng endpoint này để tạo hình ảnh tĩnh thông qua API tạo hình ảnh của Kling. Endpoint này hỗ trợ cả yêu cầu chỉ dùng văn bản và yêu cầu dùng ảnh tham chiếu thông qua cùng một luồng tác vụ bất đồng bộ. ## Yêu cầu đầu tiên Bắt đầu với `model_name: kling-v3`, `prompt`, `n` và `aspect_ratio`. Chỉ thêm ảnh tham chiếu, các thiết lập độ trung thực hoặc các trường nâng cao sau khi yêu cầu đầu tiên trả về một tác vụ có thể sử dụng được. Nếu bỏ qua `model_name`, hệ thống sẽ dùng một giá trị mặc định tương thích cũ, vì vậy hãy gửi rõ ràng `kling-v3` cho các tích hợp mới. ## Đọc phản hồi Lưu `task_id` được trả về, sau đó poll route truy vấn hình ảnh Kling tương ứng cho đến khi `task_status` đạt trạng thái kết thúc. Nếu quy trình của bạn cần lưu trữ bền vững, hãy sao chép asset cuối cùng vào lớp lưu trữ của riêng bạn sau khi quá trình tạo hoàn tất. ## OpenAPI ````yaml api/openapi/image/kling/post-image-generation.openapi.json POST /kling/v1/images/generations openapi: 3.1.0 info: title: Kling Image Generation API version: 1.0.0 servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /kling/v1/images/generations: post: summary: Generate images with Kling operationId: kling_image_generation parameters: - name: Content-Type in: header required: false description: Must be `application/json`. schema: type: string default: application/json requestBody: required: true content: application/json: schema: type: object required: - prompt properties: model_name: type: string description: >- Kling image model variant. Use `kling-v3` for new requests. Omitting `model_name` uses the legacy CometAPI route default. enum: - kling-v1 - kling-v1-5 - kling-v2 - kling-v2-1 - kling-v3 default: kling-v1 prompt: type: string description: >- Text prompt describing the image to generate. Maximum 2500 characters. negative_prompt: type: string description: >- Elements to exclude from the image. Maximum 2500 characters. Not supported when `image` is provided. image: type: string description: >- Reference image as a raw Base64 string without a `data:` prefix, or a public URL. Accepted formats: JPG, JPEG, PNG. Maximum 10 MB, minimum 300x300 px, aspect ratio between 1:2.5 and 2.5:1. image_reference: type: string description: >- Reference mode for legacy image-to-image requests when `image` is provided. enum: - subject - face image_fidelity: type: number description: >- How closely the output follows the reference image. Range: 0-1. Used by legacy image-reference models. default: 0.5 minimum: 0 maximum: 1 human_fidelity: type: number description: >- Human-subject fidelity control. Range: 0-1. Used only by legacy subject-reference requests. default: 0.45 minimum: 0 maximum: 1 element_list: type: array description: >- Optional Kling element references. The total count of element references and input images must not exceed 10. items: type: object required: - element_id properties: element_id: type: integer description: Kling element ID. resolution: type: string description: Output resolution. Defaults to `1k`. enum: - 1k - 2k default: 1k 'n': type: integer description: 'Number of images to generate. Range: 1-9.' minimum: 1 maximum: 9 default: 1 aspect_ratio: type: string description: Output aspect ratio (width:height). enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' - '3:2' - '2:3' - '21:9' default: '16:9' watermark_info: type: object description: Watermark options. properties: enabled: type: boolean description: Whether to add the official watermark. callback_url: type: string description: >- Webhook URL to receive task status updates when the task completes. external_task_id: type: string description: >- Optional user-defined task ID for your own tracking. Must be unique per account. default: model_name: kling-v3 prompt: A paper boat floating on calm water at sunrise 'n': 1 aspect_ratio: '1:1' examples: Default: summary: Text-to-image request value: model_name: kling-v3 prompt: A paper boat floating on calm water at sunrise 'n': 1 aspect_ratio: '1:1' responses: '200': description: Task request accepted or an error response returned by the API. content: application/json: schema: type: object required: - code - message - data properties: code: oneOf: - type: integer - type: string description: Response code. `0` means the task request was accepted. message: type: string description: Response message. request_id: type: string description: Request identifier returned when present. data: type: object required: - task_id - task_status - created_at - updated_at properties: task_id: type: string description: System-generated task ID. task_status: type: string description: Task status. enum: - submitted - processing - succeed - failed task_status_msg: oneOf: - type: string - type: 'null' description: Task status detail when present. task_info: type: object properties: external_task_id: oneOf: - type: string - type: 'null' description: Caller-provided external task ID when supplied. additionalProperties: true task_result: oneOf: - type: object additionalProperties: true - type: 'null' description: Task result payload after the task completes. created_at: type: integer description: >- Task creation time as a Unix timestamp in milliseconds. updated_at: type: integer description: Task update time as a Unix timestamp in milliseconds. additionalProperties: true additionalProperties: true x-codeSamples: - lang: Shell label: Default source: | curl https://api.cometapi.com/kling/v1/images/generations \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ -d '{ "model_name": "kling-v3", "prompt": "A paper boat floating on calm water at sunrise", "n": 1, "aspect_ratio": "1:1" }' - lang: Python label: Default source: | import os import requests response = requests.post( "https://api.cometapi.com/kling/v1/images/generations", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "model_name": "kling-v3", "prompt": "A paper boat floating on calm water at sunrise", "n": 1, "aspect_ratio": "1:1" }, ) result = response.json() print(result["code"], result.get("data", {}).get("task_id")) - lang: JavaScript label: Default source: > const response = await fetch("https://api.cometapi.com/kling/v1/images/generations", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model_name": "kling-v3", "prompt": "A paper boat floating on calm water at sunrise", "n": 1, "aspect_ratio": "1:1" }), }); const result = await response.json(); console.log(result.code, result.data?.task_id); components: securitySchemes: bearerAuth: type: http scheme: bearer description: Bearer token authentication. Use your CometAPI key. ````