Which Google models does the media-gen skill support?

The skill supports Gemini 2.5 Flash, Gemini 3.0 Pro, Imagen 3.0 for images, and Veo 3.1 (Standard and Fast) for video generation.

Is negative prompting supported?

Negative prompts are supported when using the Imagen 3.0 and Veo 3.1 models to help exclude specific elements from the output.

What credentials are required to use this skill?

You need a valid Google AI Studio API key configured as either a GEMINI_API_KEY or GOOGLE_API_KEY environment variable.

How does the skill handle long-running video tasks?

Video generation is handled asynchronously; the script automatically polls the status at set intervals until the generation is complete.

Can I control the dimensions of the generated media?

Yes, you can specify aspect ratios such as 1:1, 16:9, 9:16, or 4:3 using the --aspect-ratio parameter.

Google Media Gen

Name: Google Media Gen
Author: ninyawee

byninyawee

Herramientas de Diseño

Generates high-quality images and videos using Google GenAI models like Imagen and Veo directly within Claude.

Acerca de

Media-gen is a specialized Claude Code skill that integrates Google’s Generative AI SDK to streamline multimedia creation within your development workflow. It empowers users to generate high-fidelity images and cinematic videos via simple commands, leveraging models such as Gemini 2.5/3.0, Imagen 3.0, and Veo 3.1. Whether you need rapid UI placeholders, marketing assets, or animated previews, this skill handles model selection, aspect ratio adjustments, negative prompting, and asynchronous video polling automatically, transforming Claude into a comprehensive creative studio.

Características Principales

Multi-model image generation using Gemini 3.0 Pro and Imagen 3.0
Cinematic video production with Veo 3.1 and Veo 3.1 Fast models
Customizable aspect ratios including 1:1, 16:9, 9:16, and 4:3
Advanced prompting support with negative prompts for Imagen and Veo
Image-to-video capabilities for animating static reference images
0 GitHub stars

Casos de Uso

Automating the creation of video previews or transitions for presentations
Prototyping visual assets and UI placeholders for frontend development
Generating marketing materials and social media content from text prompts

Acerca de

Características Principales

Multi-model image generation using Gemini 3.0 Pro and Imagen 3.0
Cinematic video production with Veo 3.1 and Veo 3.1 Fast models
Customizable aspect ratios including 1:1, 16:9, 9:16, and 4:3
Advanced prompting support with negative prompts for Imagen and Veo
Image-to-video capabilities for animating static reference images
0 GitHub stars

Casos de Uso

Automating the creation of video previews or transitions for presentations
Prototyping visual assets and UI placeholders for frontend development
Generating marketing materials and social media content from text prompts