Shotstack Generate API - Early Access Waitlist

We have been seeing a lot of excitement around text-to-image and text-to-video AI models on the internet lately. We find these machine learning techniques incredibly exciting and are blown away by the potential of adding these types of capabilities into your applications.

These models are a little tricky to get your head around and over the last couple weeks we’ve been playing around with these models and looking for ways to make these more accessible to developers.

Thus, we are excited to announce the Shotstack Generate API.

The Generate API is a powerful API designed to allow developers easy access to the latest diffusion models and allowing you to easily integrate these capabilities into your own applications.

We’ve opened up early access so you have the opportunity to test this out yourself:

Apply for early access

Apply for early access today

Text to Image Generation

The image generation endpoint takes advantage of the latest text-to-image diffusion models allowing you to create realistic images and art from a description in natural language.

POST https://api.shotstack.io/v1/generate

{
    "prompt": "A car driving through the mountains"
}
{
    "success": true,
    "message": "Created",
    "response": {
        "status": "done",
        "url": "https://shotstack-ai-models.s3.ap-southeast-2.amazonaws.com/z33knba4tb/8dbf020f-b2b0-4e63-89c0-c82aab7d2af7.png"
    }
}

Text to Video Generation

Stay tuned for updates on our Text to Video generation API, allowing you to use natural language to generate realistic videos.

Good news!
It will absolutely help us to create unique videos.

1 Like

Yes, and if we can submit an image as a style for the AI to learn from, it would be a master stroke. I have been working on a model which utilizes past images attached to a certain user and a certain project to gradually learn what the user is trying to create. Been using tensor flow, and would love to see how it could integrate with what you guys are doing.

1 Like