VideoFusion API

Overview

The VideoGen endpoint provides a suite of powerful tools to generate videos using various methods, such as text prompts, images, or trained models. Below are the available endpoints:

• Create long videos - Scene Maker
• Generate videos from text prompts
• Generate videos from images
• Upload video data in base64 format and retrieve a URL
• Generate high quality videos from text prompts
• Fetch queued and processing video requests

Available Endpoints

Text to Video

Create videos from a text prompt using trained or public models. Description: Generate videos by providing a descriptive text prompt.

Endpoint in Action

Image to Video

Generate videos based on input images. Description: Create videos by supplying an image as the input.

Endpoint in Action

Text to Video Ultra

Text to Video Ultra endpoint helps generate HD video, with high quality and high resolution, from a given text prompt. Description: Generate videos by providing a descriptive text prompt.

Scene Maker

Generate scenes for video creation from structured input. Description: Create a sequence of scenes using structured inputs.

Base64 to URL

Upload video data in base64 format and retrieve a URL. Description: Convert base64 video data into a URL for easy sharing and access.

Fetch Video

This endpoint to fetch queued and processing video requests. Description: Fetch metadata and progress for pending video generation requests.

Playground

You can try the available endpoints in our Playground section, just make sure to sign up first.