gemini-imagegen

Generate and edit images via the Gemini API with configurable aspect ratios.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Folly-Partners/claudesync --skill gemini-imagegen-folly-partners
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/Folly-Partners/claudesync/tree/main/plugins/cache/every-marketplace/compound-engineering/2.23.1/skills/gemini-imagegen
Command: npx skills add https://github.com/Folly-Partners/claudesync --skill gemini-imagegen-folly-partners

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, Pillow, and includes scripts (resource) components.

What problem does it solve?

This Skill enables generating and editing images using the Gemini API to automate creative workflows across marketing, product design, and branding.

Core Features & Use Cases

  • Image generation: Create high-quality images from text prompts with configurable aspect ratios and resolutions.
  • Image editing & refinement: Modify existing images or compose multiple references through guided prompts.
  • Multi-turn refinement & prompts: Iterate on outputs using a chat-like interaction to reach the desired result.
  • Use Case: Designers produce social media visuals and logos by prompting Gemini to generate variations, then refine selections.

Quick Start

Use the gemini-imagegen skill to generate a hero image for a landing page given a prompt like "sleek tech product on a white background".

Frequently Asked Questions about gemini-imagegen

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

FAQPage Schema
How do I generate images using the Gemini API?

Image generation with the Gemini API converts text prompts into high-quality images with configurable aspect ratios and resolutions. Use the gemini-imagegen skill with a text description to create variations for marketing, branding, or design work. Requires a GEMINI_API_KEY and supports gemini-3-pro-image-preview or gemini-2.5-flash-image models.

Can I edit and refine existing images with Gemini?

Yes. Image editing and refinement with Gemini allows you to modify existing images or compose multiple references through guided prompts. Iterate on outputs using multi-turn chat-like interactions until you reach your desired result for logos, social media visuals, or product mockups.

What does it take to start generating images with Gemini API?

To start, you need a GEMINI_API_KEY for authentication, the google-genai dependency to interface with Gemini's models, and Pillow for image handling. The skill supports flexible aspect_ratio and image_size options for both gemini-3-pro-image-preview and gemini-2.5-flash-image models.

What are the limitations of AI image generation with Gemini?

Output quality depends on prompt clarity and model capability. Gemini API has rate limits and usage quotas tied to your API key. Complex or highly specific design requests may require multiple refinement iterations, and some creative constraints apply based on Gemini's content policies.

How does multi-turn refinement improve image outputs?

Multi-turn refinement enables iterative chat-like prompting where you guide Gemini toward your vision through successive adjustments. Each interaction refines the previous output, letting you specify style tweaks, composition changes, or element modifications without regenerating from scratch.