What resolutions and aspect ratios are supported?

The skill supports 1K, 2K, and 4K resolutions, with aspect ratios ranging from square (1:1) and cinematic (21:9) to portrait (9:16).

What model does this skill use for image generation?

It uses the gemini-3-pro-image-preview model by default for all generation and editing tasks to ensure the highest quality results.

Why are my saved images showing media type errors?

The Gemini API returns images in JPEG format by default. You must save files with a .jpg extension to avoid format mismatch errors.

Does it support creating images based on real-time data?

Yes, by using the Google Search grounding feature, you can generate images like infographics based on current real-world information.

Can I edit existing images with this skill?

Yes, the skill supports image editing by passing existing files along with natural language text prompts to describe the desired modifications.

Gemini AI Image Generation

Name: Gemini AI Image Generation
Author: Folly-Partners

byFolly-Partners

デザインツール

Generates and edits high-quality images using the Gemini Pro API directly within your development environment.

概要

This skill integrates Google's Gemini Pro image generation capabilities into Claude, allowing developers to create, edit, and refine visual assets using natural language. It supports advanced features like multi-turn image refinement, composition from up to 14 reference images, and Google Search grounding for real-time visual data. Whether you need photorealistic scenes, UI mockups, or logo designs, this skill provides precise control over resolution (up to 4K) and aspect ratios, ensuring seamless integration of AI-generated visuals into your software development workflow.

主な機能

Multi-turn refinement for iterative image editing and chat-based styling
High-resolution generation up to 4K using Gemini-3-Pro-Image-Preview
Integrated Google Search grounding for data-driven infographics and visuals
Precise control over aspect ratios and camera-specific photorealistic prompting
Multi-image composition support using up to 14 reference files
0 GitHub stars

ユースケース

Iterative image manipulation and style transfer for existing visual assets
Generating unique logos, icons, and marketing graphics for applications
Rapid prototyping of UI/UX assets, stickers, and product mockups

概要

主な機能

Multi-turn refinement for iterative image editing and chat-based styling
High-resolution generation up to 4K using Gemini-3-Pro-Image-Preview
Integrated Google Search grounding for data-driven infographics and visuals
Precise control over aspect ratios and camera-specific photorealistic prompting
Multi-image composition support using up to 14 reference files
0 GitHub stars

ユースケース

Iterative image manipulation and style transfer for existing visual assets
Generating unique logos, icons, and marketing graphics for applications
Rapid prototyping of UI/UX assets, stickers, and product mockups