Skip to main content

video models

Framepack API / Video generation from image with next frame prediction

Generate high-quality longer videos from images with Framepack AI. Access the Framepack API with to create consistent video sequences today!

Get Started!

Framepack API Pricing

Pricing is calculated per second of generated video.

Img2Videoper second

$0.03

    Framepack API Features

    Capabilities from the production model page.

    Multimodal Input

    Framepack video API supports multimodal input, turning your image and text prompt into high quality videos.

    Long Video Generation

    Framepack AI API supports long video generation and flexible duration generation options. Choose generation from 10 to 30 seconds at 30 FPS.

    Advanced Training Method

    Framepack AI is robustly trained on advanced methods for anti-drifting and anti-forgetting to ensure that video results maintain consistency and quality throughout their duration.

    Next Frame Prediction

    Framepack AI video utilizes next frame prediction for I2V generations to autoregressively generate video ensuring efficiency and quality.

    Get started

    Create your API key

    Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.

    Top up credits

    Add credits on the billing page when you are ready to scale beyond the free tier.

    Call the API

    POST your first task following the API docs, then poll the task until the result is ready.

    Iterate in the playground

    Prototype prompts and settings in the the playground above before wiring them into your product.

    curl -X POST 'https://api.piapi.ai/api/v1/task' \
      -H 'X-API-Key: YOUR_API_KEY' \
      -H 'Content-Type: application/json' \
      -d '{
        "model": "Qubico/framepack",
        "task_type": "img2video",
        "input": {
          "start_image": "YOUR_IMAGE_URL",
          "prompt": "The camera slowly zooms in on a calm portrait.",
          "duration": 10
        }
      }'
    
    # → { "task_id": "9d5a…", "status": "pending" }

    Framepack API Frequently Asked Questions

    What is Framepack?

    Framepack is an I2V model that turns still images into videos. It is trained for long video generation. Get started with the Framepack AI API or try out a demo with the Framepack AI video generator playground!

    What does the Framepack API cost?

    Pricing is $0.03 per second of generated video. You only pay for the duration you request. Duration selection is flexibility between 10 to 30 seconds.

    What image format does the API accept?

    You can provide the start image and optionally the end image as a URL or as a base64-encoded string. Use clear, well-lit images. Faces and human subjects generally give the best results.

    Are there refunds?

    No, we do not offer refunds. But when you first sign up for an account on PiAPI's Workspace, you are given free credits to try our playground and our API (specifically the "Pay-as-you-go" service) before making payments!

    How can I get in touch with your team?

    Please email us at support@piapi.ai - we'd love to talk more regarding our product offering!

    More questions? See the API docs.

    Our blog

    Framepack API