> ## 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.
# 建立 Kling 圖生影片任務
> 透過 CometAPI POST /kling/v1/videos/image2video，將單張圖片轉換為 Kling 影片，並支援非同步任務建立與依 task ID 追蹤進度。
使用此端點可將一張來源圖片製作成動畫並生成 Kling 影片。
## 呼叫前準備
* 提供一個公開圖片 URL 或一個 base64 圖片字串
* 使用符合 Kling 像素要求的圖片；過小的縮圖會被生成任務拒絕
* 先從預設的 `kling-v2-6` 範例開始，當你需要不同模型路線時，再從 OpenAPI enum 中選擇其他 `model_name`
* 保持第一次請求簡單：一張輸入圖片、一個 prompt、無尾幀、無動作遮罩
* 當你需要可控的局部動作時，使用 `dynamic_masks` 作為由遮罩與軌跡物件組成的陣列
* 對於支援生成聲音的模型路線，第一個請求可使用 `sound: off` 來實現可重現且無音訊的結果
## 模型命名
在此端點上請使用一般的 Kling 影片 model ID。Omni model ID 請保留給 [Omni Video](./omni-video)。
## 任務流程
建立任務並儲存回傳的 Kling `task_id`。
接著使用 [取得 Kling 任務](./individual-queries) 持續追蹤任務狀態，直到輸出準備完成。
如果你需要在供應商交付 URL 的保留期限之外繼續保存資產，請持久化儲存已完成的成品。
完整參數參考請見[官方 Kling 文件](https://kling.ai/document-api/apiReference/model/imageToVideo)。
## OpenAPI
````yaml api/openapi/video/kling/post-image-to-video.openapi.json POST /kling/v1/videos/image2video
openapi: 3.1.0
info:
title: Image to Video API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/kling/v1/videos/image2video:
post:
summary: Create a Kling image-to-video task
description: Submit one source image and receive a task id for later polling.
operationId: image_to_video
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- image
properties:
prompt:
type: string
description: >-
Text prompt describing the desired motion. Maximum 500
characters.
negative_prompt:
type: string
description: Elements to exclude from the video. Maximum 200 characters.
image:
type: string
description: >-
Source image URL or base64 image string. Use an image that
meets Kling pixel requirements; very small thumbnails are
rejected. For base64 input, send the encoded image string as
the field value.
callback_url:
type: string
description: >-
Webhook URL to receive task status updates when the task
completes.
mode:
type: string
description: >-
Generation mode. `std` for standard (faster), `pro` for
professional (higher quality).
enum:
- std
- pro
default: std
model_name:
type: string
description: >-
Model ID for this image-to-video request. Use `kling-v3` for
new requests. Use Omni model IDs only with the Omni Video
endpoint.
enum:
- kling-v1
- kling-v1-5
- kling-v1-6
- kling-v2-master
- kling-v2-1
- kling-v2-1-master
- kling-v2-5-turbo
- kling-v2-6
- kling-v3
default: kling-v1
image_tail:
type: string
description: >-
Tail-frame reference image as a Base64 string or public URL.
Same format requirements as `image`. Controls the last frame
of the generated video.
cfg_scale:
type: number
description: >-
Prompt adherence strength. Higher values follow the prompt
more closely. Range: 0–1.
duration:
type: string
description: >-
Output video length in seconds. Use `5` or `10`; omit to use
`5`.
default: '5'
static_mask:
type: string
description: >-
Static brush mask image as a Base64 string or public URL.
White areas are frozen in place during video generation.
Must match the aspect ratio and resolution of the input
image.
dynamic_masks:
type: array
description: >-
Optional motion masks. Each entry contains a mask image and
an ordered trajectory list.
items:
type: object
required:
- mask
- trajectories
properties:
mask:
type: string
description: Mask image URL or base64 string for the moving area.
trajectories:
type: array
description: Trajectory points for the masked area.
items:
type: object
required:
- x
- 'y'
properties:
x:
type: integer
description: Horizontal coordinate.
'y':
type: integer
description: Vertical coordinate.
external_task_id:
type: string
description: >-
Custom task id for your own tracking. Does not replace the
system-generated task id but can be used to query tasks.
Must be unique per user.
sound:
type: string
description: >-
Optional generated-audio switch for models that support
video sound. Use `on` or `off`, or omit the field for the
model default.
enum:
- 'on'
- 'off'
default:
image: https://your-image-host/source.jpg
prompt: A cinematic slow push-in on the subject
model_name: kling-v3
mode: pro
duration: '5'
sound: 'off'
examples:
Default:
summary: Image-to-video request with generated sound disabled
value:
image: https://your-image-host/source.jpg
prompt: A cinematic slow push-in on the subject
model_name: kling-v3
mode: pro
duration: '5'
sound: 'off'
responses:
'200':
description: Task accepted.
content:
application/json:
schema:
type: object
required:
- code
- message
- data
properties:
code:
type: integer
description: Error code; specifically define the error code
message:
type: string
description: error message
data:
type: object
required:
- task_id
- task_status
- created_at
- updated_at
properties:
task_id:
type: string
description: Task ID, system generated
task_status:
type: string
description: >-
Task status, enumerated values: submitted, processing,
succeed, failed.
task_status_msg:
type: string
task_info:
type: object
additionalProperties: true
created_at:
type: integer
description: Task creation time, Unix timestamp, in ms.
updated_at:
type: integer
description: Task update time, Unix timestamp, in ms.
example:
code: 0
message: success
data:
task_id: '2032273942220931072'
task_status: submitted
task_info: {}
created_at: 1773366840306
updated_at: 1773366840306
x-codeSamples:
- lang: Shell
label: Default
source: |
curl https://api.cometapi.com/kling/v1/videos/image2video \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"image": "https://your-image-host/source.jpg",
"prompt": "A cinematic slow push-in on the subject",
"model_name": "kling-v3",
"mode": "pro",
"duration": "5",
"sound": "off"
}'
- lang: Python
label: Default
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/kling/v1/videos/image2video",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
json={
"image": "https://your-image-host/source.jpg",
"prompt": "A cinematic slow push-in on the subject",
"model_name": "kling-v3",
"mode": "pro",
"duration": "5",
"sound": "off"
},
)
result = response.json()
print(result.get("code"), result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Default
source: >
const response = await
fetch("https://api.cometapi.com/kling/v1/videos/image2video", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"image": "https://your-image-host/source.jpg",
"prompt": "A cinematic slow push-in on the subject",
"model_name": "kling-v3",
"mode": "pro",
"duration": "5",
"sound": "off"
}),
});
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.
````