Video Models

Previousstable-diffusion-v35-large NextAlibaba Cloud

Last updated 1 month ago

Video Models

Overview

With our API you can generate videos from your prompt and imagination.

We support multiple video models. You can find the complete list along with API reference links at the end of the page.

Example

Full example explanation

As an example, we will generate a video using the popular video-01 model from the Chinese company MiniMax. This model, as you can verify by checking its API Reference, accepts an image as input (serving as the first frame of the future video) along with a text prompt, where we can describe what should happen to this image throughout the video.

We used a publicly available image from Wikimedia and described in the prompt that the cheetah turns toward the camera.

A notable feature of video-01 model is that video generation and retrieving the final video file from the server are done through separate API calls. (LAPLAS API tokens are only consumed during the first step—i.e., the actual video generation.)

You can insert the contents of each of the two code blocks into a separate Python file in your preferred development environment (or, for example, place each part in a separate cell in Jupyter Notebook). Replace <YOUR_API_KEY> in both fragments with the LAPLAS API Key obtained from your account.

Next, run the first code block. If everything is set up correctly, you will see the following line in the program output (the specific numbers, of course, will vary): Generation: {'generation_id': '234954179076239'}

This means that our generation has been queued on the server.

Now, copy this numerical value (without quotation marks) and insert it into the second code block, replacing <GENERATION_ID>. Now, we can execute the second code block to request our final video file from the server.

Processing the request on the server may take some time (usually less than a minute). If the requested file is not yet ready, the output will display the corresponding status. Try waiting a bit and rerun the second code block. (If you're comfortable with coding, you can modify the script to perform this request inside a loop.)

In our case, after three reruns of the second code block (waiting a total of about 20 seconds), we saw the following output:

Generation: {'id': '234954179076239', 'status': 'completed', 'video': {'url': 'https://cdn.apilaplas.com/whale/inference_output%2Fvideo%2F2025-02-07%2F0c4d54db-da1b-404a-a495-600426796415%2Foutput.mp4?Expires=1738947643&OSSAccessKeyId=LTAI5tAmwsjSaaZVA6cEFAUu&Signature=mo3sfeNpVz5mNQW%2BSt2g8d2%2Fvf4%3D'}}

As you can see, the 'status' is now 'completed', and further in the output line, we have a URL where the generated video file can be downloaded.

Here is the resulting turning cheetah (original 960x720px):

The first code block (generation):


import requests


def main():
    url = "https://api.apilaplas.com/v2/generate/video/minimax/generation"
    payload = {
        "model": "video-01",
        "prompt": "Cheetah turns toward the camera.",
        "first_frame_image": "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a9/Cheetah4.jpg/1200px-Cheetah4.jpg",
    }
    # Insert your LAPLAS API Key instead of <YOUR_LAPLASAPI_KEY>:
    headers = {"Authorization": "Bearer <YOUR_LAPLASAPI_KEY>", "Content-Type": "application/json"}

    response = requests.post(url, json=payload, headers=headers)
    print("Generation:", response.json())


if __name__ == "__main__":
    main()

The second code block (retrieving the generated video file from the server):

import requests


def main():
    url = "https://api.apilaplas.com/v2/generate/video/minimax/generation"
    params = {
        # Insert the generation_id (that was returned by the generation part above) in the quotation marks instead of <GENERATION_ID>:
        "generation_id": "<GENERATION_ID>",
    }
    
    # Insert your LAPLAS API Key instead of <YOUR_LAPLASAPI_KEY>:
    headers = {"Authorization": "Bearer <YOUR_LAPLASAPI_KEY>", "Content-Type": "application/json"}

    response = requests.get(url, params=params, headers=headers)
    print("Generation:", response.json())


if __name__ == "__main__":
    main()

All Available Video Models

Model ID

Developer

Context

Model Card

Kling AI

Minimax AI

Runway

Alibaba Cloud

Google

Previousstable-diffusion-v35-large NextAlibaba Cloud

Last updated 1 month ago