Skip to main content

​
Introduction to Gemini

Welcome to the Gemini service documentation! This service integrates Gemini AI, a powerful tool for generating images and videos. Whether you’re looking to generate creative images, edit videos, or explore new content creation capabilities, Gemini provides the ideal tools for your project.

​
Features

Gemini AI offers advanced image and video generation tools to enhance your creative work:
  • Generate Images: Create images using advanced AI models like Nana and Bananana. These models excel in generating high-quality, creative images based on text prompts or predefined styles.
  • Generate Videos: Use Veo2 and Veo3 models to create video content from text descriptions or by editing existing clips. These models are designed for high-quality video generation and offer various customization options.
  • Video Task Management: Track and monitor the status of your video generation tasks to ensure smooth processing.
  • Advanced Editing: Modify and refine both your videos and images with advanced features such as filters, effects, and more.

​
How to Use Gemini

To get started with Gemini, follow these simple steps:
  1. Create a New Task: Start by creating a task to generate images or videos.
  2. Track Task Status: Keep track of the task’s progress to know when your content is ready for download.
  3. Download and Use: Once your task is complete, you can download the generated image or video for use in your project.

​
Available Endpoints

Here are the API endpoints for interacting with Gemini:

​
Image and Video Generation API

  • Generate Image with Nana or Bananana Model
    POST /gemini/image
    Create an image using Nana or Bananana models. Both models are optimized for generating creative, high-quality images based on your text prompts.
  • Generate Video with Veo2 or Veo3 Model
    POST /gemini/video
    Create a video clip from a description or existing content. You can choose between the Veo2 or Veo3 models for video generation, with Veo3 providing enhanced quality and flexibility.
  • Get Video Task Status
    GET /gemini/task
    Retrieve the current status of your video generation task.
  • Advanced Editing Operations
    POST /gemini/task
    Perform editing operations on generated content, such as applying filters, effects, or adjustments.

​
Explore the API Documentation

For detailed documentation on how to use these endpoints, click the links below:
For more details, visit the full Gemini API Documentation.