gemini-imagegen

Generate and edit images via the Gemini API with JPEG or PNG outputs.

12|2|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/jikig-ai/soleur --skill gemini-imagegen-jikig-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/jikig-ai/soleur/tree/main/plugins/soleur/skills/gemini-imagegen
Command: npx skills add https://github.com/jikig-ai/soleur --skill gemini-imagegen-jikig-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Programmatic image generation and editing can be fragmented and error-prone when dealing with API quotas, model choices, file formats, and iterative refinements. This Skill centralizes generation, editing, composition, and multi-turn refinement workflows against Google's Gemini API while providing quota checks, error handling, and format guidance to ensure reliable outputs.

Core Features & Use Cases

  • Text-to-Image Generation: Create photorealistic or stylized images from prompts with configurable aspect ratio and resolution.
  • Image Editing & Multi-Turn Refinement: Edit existing images conversationally and refine outputs across interactive chat sessions.
  • Composition & Style Transfer: Combine up to 14 reference images for composite scenes or transfer artistic styles between images, ideal for product mockups, logos, stickers, and marketing assets.
  • Robustness: Includes quota checking, explicit error mapping for common API failures, and guidance to save Gemini JPEG outputs correctly or convert to PNG when required.

Quick Start

Generate a 1K square product mockup of a red sneaker and save the result as output.jpg using the gemini-imagegen scripts.

Frequently Asked Questions about gemini-imagegen

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

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

To generate and iteratively refine images with the Gemini API, you can use multi-turn conversational editing to apply text-to-image generation and modify outputs interactively across chat sessions.

Can I combine multiple reference images for style transfer and product mockups with Gemini?

Yes, you can combine up to 14 reference images for composite scenes, style transfer, product mockups, and logo design using the Gemini API to produce cohesive visual assets.

Do I need a specific API key and Python libraries to run Gemini image generation scripts?

Yes, you need a GEMINI_API_KEY along with the google-genai and Pillow Python libraries to execute image generation scripts, handle quota verification, and manage API error mapping.

Why does my Gemini API image generation fail during multi-turn editing?

Gemini API image generation may fail due to exceeded API quotas or unmapped errors; this workflow includes quota checking and explicit error mapping for common failures to ensure reliable outputs.

What is the default file format for Gemini image outputs and can I convert them?

Gemini image outputs default to JPEG format, but you can explicitly convert them to PNG when needed using the Pillow library to ensure correct format handling for your visual assets.