How does this skill improve my workflow?

It integrates a powerful image generator directly into your development workflow, allowing you to create and refine visual assets without switching contexts. Features like conversational editing and grounding with real-time Google Search data accelerate the creative process.

What does the Gemini Image Generation skill do?

This skill enables Claude to generate and edit high-quality images using Google's Gemini API. It allows you to create new visuals from text prompts, modify existing photos, and refine designs through a conversational, multi-turn process.

What are the key capabilities of this skill?

Its core capabilities include text-to-image generation (up to 4K resolution), image editing with reference photos, iterative refinement via chat, composing scenes from multiple images, and generating visuals grounded in real-time Google Search data.

When should I use this skill?

Use this skill for any image creation or manipulation task. It's ideal for generating photorealistic scenes, creating stylized art and stickers, designing logos with text, making product mockups, or applying edits to existing images.

Gemini Image Generation

Name: Gemini Image Generation
Author: EveryInc

byEveryInc

•

2,824

•

デザインツール

Generates and edits high-quality images from text prompts, existing photos, and real-time data using the Gemini API.

Leverage Google's Gemini API for a wide range of image generation and manipulation tasks. This skill enables the creation of images from text prompts, iterative editing of existing images through multi-turn conversations, and composition from multiple source images. It supports various resolutions (up to 4K) and aspect ratios, making it ideal for creating logos, product mockups, stylized art, and photorealistic scenes. Advanced features include grounding prompts with real-time Google Search data for dynamic content generation.

主な機能

01Includes best practices for prompting photorealistic scenes, stylized art, and text-in-image generation

02Multi-turn conversational refinement for iterative image editing

032,824 GitHub stars

04Text-to-image generation with customizable resolution (up to 4K) and aspect ratios

05Grounds image generation with real-time Google Search data

06Image editing and composition using one or more reference images

ユースケース

01Generating stylized or photorealistic artwork from detailed text descriptions

02Editing existing photos by adding or modifying elements through conversational prompts

03Creating marketing assets like product mockups, logos, or stickers

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add everyinc/compound-engineering-plugin gemini-imagegen

For use in Claude.ai and ChatGPT

Download Skill