generate-media

Generate and edit images and videos using Gemini and Veo models.

15|3|Updated Aug 28, 2025

Search Tags:#editing #image #video #generation #gemini #veo

Ready to run

npx skills add https://github.com/cheatcode-ai/cheatcode --skill generate-media-cheatcode-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: generate-media
Source: https://github.com/cheatcode-ai/cheatcode/tree/main/skills/generate-media
Command: npx skills add https://github.com/cheatcode-ai/cheatcode --skill generate-media-cheatcode-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill removes the technical friction from visual content creation by allowing you to generate, edit, and extend high-quality images and videos through natural language prompts.

Core Features & Use Cases

Generative Visuals: Create photorealistic images or cinematic video clips from scratch using advanced AI models.
Intelligent Editing: Perform inpainting, style transfers, and object modifications on existing images without needing complex design software.
Video Extension: Seamlessly extend the duration of generated video clips while maintaining visual consistency.

Quick Start

Use the generate-media skill to create a photorealistic landscape image of a mountain range at sunset with a 16:9 aspect ratio.

Frequently Asked Questions about generate-media

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

FAQPage Schema

How do I generate images and videos using natural language prompts?▼

Generate images and videos by providing natural language prompts to the generate-media skill, which utilizes Gemini and Veo models to create photorealistic visuals and cinematic clips from scratch.

Can I perform style transfers and object modifications on existing images?▼

Perform intelligent editing on existing images using the generate-media skill, which supports inpainting, reference-guided style transfers, and object modifications without requiring complex design software.

What is the best way to extend the duration of a generated video clip?▼

Extend video duration by applying temporal video extension through the generate-media skill, which seamlessly lengthens generated clips while maintaining visual consistency across frames.

Do I need a Google API key to use Gemini and Veo models for visual generation?▼

A valid Google API key is required to execute model generation and editing tasks using the generate_or_edit_media tool within the generate-media skill workflow.

Does generate-media support aspect ratio specifications for image creation?▼

The generate-media skill supports aspect ratio specifications for image creation, allowing users to define dimensions like 16:9 when generating photorealistic landscape or cinematic visuals.

What are the limitations of using AI models for visual content creation?▼

Limitations of AI visual content creation include dependency on valid Google API keys for model execution and potential constraints in maintaining exact visual consistency during complex temporal video extensions.