kling-v2-1

Image to video

Create task

POST /kling/v1/videos/image2video

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/image2video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-2.1",
    "image": "https://example.com/start.png",
    "image_tail": "https://example.com/end.png",
    "prompt": "The subject turns and smiles",
    "negative_prompt": "blurry, distorted",
    "duration": "5",
    "mode": "pro",
    "watermark_info": {"enabled": false}
  }'

200

{"id":"860260753860210752","task_id":"860260753860210752","object":"video","model":"kling-v2-1","status":"","progress":0,"created_at":1773130665}

Request body

string

required

Must be kling-2.1.

string

required

Start-frame URL or raw Base64.

string

Optional end frame. Start-and-end-frame generation requires 1080p pro mode.

string

Positive prompt, up to 2,500 characters.

string

Negative prompt, up to 2,500 characters.

string

default:"std"

std for 720p or pro for 1080p.

string

default:"5"

5 or 10 seconds.

object

Set enabled to request an additional watermarked result.

Image requirements

Use a public URL or raw Base64 without a data URI prefix. JPG, JPEG, and PNG are supported. Files must be no larger than 10 MB, both sides at least 300 px, and the aspect ratio between 1:2.5 and 2.5:1.

Query task by ID

GET /kling/v1/videos/image2video/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/image2video/TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY'

string

required

The task ID returned by the create endpoint.

Task status is submitted, processing, succeed, or failed. Successful output is in data.task_result.videos; failure details are in data.task_status_msg. Result items contain id, url, watermark_url, and duration.

200

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request-id",
  "data": {
    "task_id": "task-id",
    "task_status": "succeed",
    "task_status_msg": "",
    "watermark_info": {"enabled": false},
    "task_result": {"videos": [{"id": "video-id", "url": "https://example.com/result.mp4", "watermark_url": "", "duration": "5"}]},
    "final_unit_deduction": "string",
    "final_balance_deduction": {"quota": "string", "list_price": "string"},
    "created_at": 1722769557708,
    "updated_at": 1722769657708
  }
}

Generated result URLs are removed after 30 days. Save the files promptly.

Kling 2.1 does not provide text-to-video. It also does not support audio, specified voices, multi-shot, motion brush, camera control, or cfg_scale.

Overview

Native Compatible Endpoints

Model APIs

Image to video

Create task

Request body

Image requirements

Query task by ID

​Image to video

​Create task

​Request body

​Image requirements

​Query task by ID

Image to video

Create task

Request body

Image requirements

Query task by ID