| --- |
| language: |
| - en |
| license: other |
| pipeline_tag: text-to-video |
| tags: |
| - kling |
| - text-to-video |
| - image-to-video |
| inference: false |
| --- |
| |
| # Kling API |
|
|
| **Model Page:** [Kling API](https://apiframe.ai/models/kling-3.0) |
|
|
| Community model card for calling Kling through a REST API. |
|
|
| This repo documents the `kling-3.0` model as exposed by Apiframe: Kuaishou's Kling Video 3.0, text-to-video and image-to-video, 3–15s, optional native audio, start/end frame control. Related ids on the same endpoint: `kling-3.0-omni`, `kling-3.0-motion-control`. |
|
|
| This repository does not host weights. Kling is a closed model. Inference runs remotely. |
|
|
| <video src="https://apiframe.ai/models-examples/kling-3-0-ember-neon-cafe.mp4" width="280" muted controls></video> |
|
|
| ## Model description |
|
|
| | | | |
| |---|---| |
| | Architecture | Kling 3.0 | |
| | Task | text-to-video; image-to-video | |
| | Output | 1 video (`videoUrl`) | |
| | Duration | 3, 5, 8, 10, or 15 seconds | |
| | Aspect ratios | `1:1`, `9:16`, `16:9` | |
| | Modes | `standard` (720p), `pro` (1080p), `4k` | |
| | Typical latency | ~135s | |
|
|
| ## How to use |
|
|
| ```bash |
| pip install requests |
| ``` |
|
|
| ```python |
| import os |
| import time |
| import requests |
| |
| API = "https://api.apiframe.ai/v2" |
| headers = { |
| "X-API-Key": os.environ["APIFRAME_API_KEY"], |
| "Content-Type": "application/json", |
| } |
| |
| job = requests.post( |
| f"{API}/videos/generate", |
| headers=headers, |
| json={ |
| "model": "kling-3.0", |
| "prompt": "a cinematic sunrise over a futuristic cityscape", |
| "klingParams": { |
| "duration": 5, |
| "mode": "pro", |
| "aspect_ratio": "16:9", |
| "generate_audio": True, |
| }, |
| }, |
| ).json() |
| |
| while True: |
| result = requests.get(f"{API}/jobs/{job['jobId']}", headers=headers).json() |
| if result["status"] in ("COMPLETED", "FAILED"): |
| break |
| time.sleep(2) |
| |
| print(result.get("result")) |
| ``` |
|
|
| `result["videoUrl"]` is the CDN URL. Pass `webhookUrl` on the generate call if you do not want to poll. |
|
|
| ### Image-to-video |
|
|
| ```python |
| import os |
| import requests |
| |
| headers = { |
| "X-API-Key": os.environ["APIFRAME_API_KEY"], |
| "Content-Type": "application/json", |
| } |
| |
| requests.post( |
| "https://api.apiframe.ai/v2/videos/generate", |
| headers=headers, |
| json={ |
| "model": "kling-3.0", |
| "prompt": "slow push in, steam rising from the cup", |
| "klingParams": { |
| "start_image": "https://example.com/frame.jpg", |
| "duration": 5, |
| "mode": "pro", |
| "aspect_ratio": "16:9", |
| }, |
| }, |
| ) |
| ``` |
|
|
| Swap `model` for `kling-3.0-omni` (reference images/video) or `kling-3.0-motion-control` (transfer motion from a clip onto a character). |
|
|
| ## Limitations |
|
|
| - Closed model. No weights, fine-tuning, or local inference. |
| - Requires an Apiframe API key (`X-API-Key`). |
| - Commercial use follows Kling's terms. |
| - Generated media is retained on the CDN for 90 days. |
|
|
| ## License |
|
|
| Outputs are subject to Kling's terms. This card is documentation only. Apiframe is not affiliated with, endorsed by, or sponsored by Kuaishou Technology. |
|
|