Kling AI Image-to-Video

Overview

Animate static images using the /v1/videos/image2video endpoint. Supports motion prompts, camera control, dynamic masks (motion brush), static masks, and tail images for start-to-end transitions.

Endpoint: POST https://api.klingai.com/v1/videos/image2video

Request Parameters

Basic Image-to-Video

import jwt, time, os, requests

BASE = "https://api.klingai.com/v1"

def get_headers():
    ak, sk = os.environ["KLING_ACCESS_KEY"], os.environ["KLING_SECRET_KEY"]
    token = jwt.encode(
        {"iss": ak, "exp": int(time.time()) + 1800, "nbf": int(time.time()) - 5},
        sk, algorithm="HS256", headers={"alg": "HS256", "typ": "JWT"}
    )
    return {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}

# Animate a landscape photo
response = requests.post(f"{BASE}/videos/image2video", headers=get_headers(), json={
    "model_name": "kling-v2-1",
    "image": "https://example.com/landscape.jpg",
    "prompt": "Clouds slowly drifting across the sky, gentle wind rustling through trees",
    "negative_prompt": "static, frozen, blurry",
    "duration": "5",
    "mode": "standard",
})

task_id = response.json()["data"]["task_id"]

# Poll for result
while True:
    time.sleep(15)
    result = requests.get(
        f"{BASE}/videos/image2video/{task_id}", headers=get_headers()
    ).json()
    if result["data"]["task_status"] == "succeed":
        print(f"Video: {result['data']['task_result']['videos'][0]['url']}")
        break
    elif result["data"]["task_status"] == "failed":
        raise RuntimeError(result["data"]["task_status_msg"])

Start-to-End Transition (image_tail)

Use image_tail to specify both the first and last frame. Kling interpolates the motion between them.

response = requests.post(f"{BASE}/videos/image2video", headers=get_headers(), json={
    "model_name": "kling-v2-master",
    "image": "https://example.com/sunrise.jpg",        # first frame
    "image_tail": "https://example.com/sunset.jpg",    # last frame
    "prompt": "Time lapse of sun moving across the sky",
    "duration": "5",
    "mode": "professional",
})

Motion Brush (dynamic_masks)

Draw motion paths for specific elements in the image. Up to 6 motion paths per image in v2.6.

response = requests.post(f"{BASE}/videos/image2video", headers=get_headers(), json={
    "model_name": "kling-v2-6",
    "image": "https://example.com/person-standing.jpg",
    "prompt": "Person walking forward naturally",
    "duration": "5",
    "dynamic_masks": [
        {
            "mask": "https://example.com/person-mask.png",  # white = selected region
            "trajectories": [
                {"x": 0.5, "y": 0.7, "t": 0.0},   # start position (normalized 0-1)
                {"x": 0.5, "y": 0.5, "t": 0.5},   # midpoint
                {"x": 0.5, "y": 0.3, "t": 1.0},   # end position
            ]
        }
    ],
})

Static Mask (freeze regions)

Keep specific areas of the image static while animating the rest.

response = requests.post(f"{BASE}/videos/image2video", headers=get_headers(), json={
    "model_name": "kling-v2-master",
    "image": "https://example.com/scene.jpg",
    "prompt": "Water flowing in the river, birds flying",
    "duration": "5",
    "static_mask": "https://example.com/buildings-mask.png",  # white = frozen
})

Mutual Exclusivity Rules

These features cannot be combined in a single request:

Image Requirements

Error Handling

Resources

• Image-to-Video API
• Motion Control Guide