Google Gemini Image & Video Generation

Generate and edit images with Imagen 3 and videos with Veo 2.

4|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/armoin2018/ai-command-center --skill google-gemini-image-video-generation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Google Gemini Image & Video Generation
Source: https://github.com/armoin2018/ai-command-center/tree/main/plugins/aicc-gemini/skills/ailey-media-gemini
Command: npx skills add https://github.com/armoin2018/ai-command-center --skill google-gemini-image-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generates and manages AI-driven media content using Google Gemini across multiple tiers, streamlining production, editing, and upscaling workflows.

Core Features & Use Cases

  • Image generation with Imagen 3 from prompts in multiple aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4)
  • Video generation with Veo 2, plus editing (inpainting, outpainting, style-transfer) and upscaling
  • Batch operations, generation history, and a feature-rich CLI for production pipelines
  • Supports Free, Pay-as-you-go, and Enterprise (Vertex AI) accounts

Quick Start

Install the skill, configure your Google Gemini API key, and run a sample generate command to start creating media.

Frequently Asked Questions about Google Gemini Image & Video Generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images and videos with Google Gemini using prompts?

To generate images and videos with Google Gemini, you configure your API key and run generate commands. It uses Imagen 3 for image generation and Veo 2 for video generation from text prompts across multiple aspect ratios.

Can I batch process multiple image generation requests with Gemini?

Yes, you can batch process multiple image generation requests with Gemini. The skill supports batch operations alongside generation history tracking and a CLI to streamline scalable media production pipelines.

Does image generation with Imagen 3 support different aspect ratios?

Image generation with Imagen 3 supports multiple aspect ratios including 1:1, 16:9, 9:16, 4:3, and 3:4. This allows you to create media content tailored for various display formats and platforms.

What video editing operations are available with Veo 2 generation?

Video editing operations available with Veo 2 generation include inpainting, outpainting, and style-transfer. The solution also supports upscaling to enhance and modify existing video content.

Do I need a specific Google Gemini account tier for media generation?

You can use Free, Pay-as-you-go, or Enterprise (Vertex AI) Google Gemini accounts for media generation. The skill implements tier-aware constraints to manage features based on your specific account level.

What is the best way to manage AI media generation history for production pipelines?

The best way to manage AI media generation history is using the skill's feature-rich CLI. It tracks generation history and handles batch operations, streamlining scalable image and video production workflows.