skills.rest
michaelvolz
michaelvolzCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-imagegen

Generate and edit images from text prompts via Gemini API endpoints.

Updated Nov 11, 2023
Search Tags:#python#composition#image-generation#multi-turn#image-editing#gemini-api#creative-tools
One-click install
npx skills add https://github.com/michaelvolz/redmuffin.Blazor.StaticWeb --skill gemini-imagegen-michaelvolz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/michaelvolz/redmuffin.Blazor.StaticWeb/tree/main/.opencode/skills/ce/gemini-imagegen
Command: npx skills add https://github.com/michaelvolz/redmuffin.Blazor.StaticWeb --skill gemini-imagegen-michaelvolz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides a clear Gemini image-generation playbook with scripts, best practices, and examples so you no longer need to stitch together prompts, config options, and API calls for creating or refining visuals.

Core Features & Use Cases

  • Gemini API playbook: Documents the default gemini-3-pro-image-preview model, supported resolutions/aspect ratios, editing workflows, multi-turn refinement, Google Search grounding, and format expectations.
  • Script toolkit: Includes generate_image, edit_image, compose_images, multi_turn_chat, and the reusable gemini_images library to cover single-shot generation, editing, composition, and interactive chats.
  • Use Case: Deliver a logo, sticker, or product mockup by refining a prompt via the chat session, merging multiple reference images, and saving the final JPEG output for stakeholder review.

Quick Start

Tell the gemini-imagegen skill to generate a 1K product mockup with a clean background and save the result as output.jpg.

Frequently Asked Questions about gemini-imagegen

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

FAQPage Schema
How do I generate AI images from text prompts using the Gemini API?▼

You generate AI images from text prompts by providing a text description to the generate_image script, which uses the Gemini API to create and save high-quality visuals directly from your input.

Can I edit existing images and merge multiple reference pictures with Gemini?▼

Yes, you can edit existing images and compose multiple reference pictures using the edit_image and compose_images scripts, orchestrating multi-turn refinement and merging via Gemini image endpoints.

What do I need to set up before using Gemini for product mockups and logo design?▼

You need to set up a GEMINI_API_KEY and install the google-genai and Pillow dependencies to orchestrate multi-turn chat, editing, and composition outputs for product mockups and logos.

Does the Gemini image generation workflow support multi-turn refinement?▼

Yes, Gemini image generation supports multi-turn refinement through the multi_turn_chat script, allowing you to iteratively refine prompts and design workflows like stickers or mockups interactively.

What is the best way to create a 1K product mockup with a clean background using Gemini?▼

The best way to create a 1K product mockup is to instruct the generation script to produce a high-quality image with a clean background and save the final JPEG output for stakeholder review.

Related Skills

Explore More Design & Creative Skills→
kolbickkolbick

nano-banana-pro

Generate and edit images using the Gemini 3 Pro Image model.

Community
Intermediate
VictaaawVictaaaw

image

Generates and optimizes marketing images for websites and social platforms using AI models.

Community
Intermediate
wangrenzhu-olawangrenzhu-ola
2

gemini-imagegen

Generate and refine images via the Gemini API with configurable parameters.

Community
Advanced
dakshrawat298-gifdakshrawat298-gif

nano-banana-pro

Automate image generation and editing via the Gemini 3 Pro Image API.

Community
Intermediate