skills.rest
jjeremycai
jjeremycaiCOMMUNITY
Explore all skills by this author →
Website𝕏@jjeremycaiGitHub

gemini-imagegen

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

Updated Aug 23, 2026
Search Tags:#refinement#image#gemini#edit#generate#mockups
One-click install
npx skills add https://github.com/jjeremycai/claudekit --skill gemini-imagegen-jjeremycai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/jjeremycai/claudekit/tree/main/plugins/compound-engineering/skills/gemini-imagegen
Command: npx skills add https://github.com/jjeremycai/claudekit --skill gemini-imagegen-jjeremycai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines image generation and editing using the Gemini API, enabling rapid creation and refinement of visuals from text prompts or reference images.

Core Features & Use Cases

  • Image generation from prompts using Gemini models (Pro recommended for highest quality and flexibility).
  • Editing and multi-turn refinement, including composition from multiple references and iterative prompts.
  • Use Case: Create a product mockup or logo by describing the concept and refining visuals through prompts.

Quick Start

Generate an image from the prompt 'A sleek modern logo for Acme Corp' using the Gemini API.

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 edit images using the Gemini API from text prompts?▼

To generate and edit images using the Gemini API, you provide text prompts to produce image and text outputs, supported by the google-genai client and Pillow library for automated visual creation.

Can I refine generated images through multi-turn prompts for logo design?▼

Yes, you can refine generated images through multi-turn iterative prompts to adjust logos and mockups, allowing step-by-step visual composition and edits based on your subsequent text instructions.

Do I need a GEMINI_API_KEY to generate mockups with this automated image generation approach?▼

Yes, you must configure a GEMINI_API_KEY in your environment to authenticate automated image generation requests and produce mockups or artwork via the Gemini API integration.

What is the best way to compose an image from multiple reference images using Gemini?▼

The best way to compose an image from multiple references is using the Gemini API's multi-turn refinement capability, which blends reference inputs iteratively to achieve your desired mockup or artwork output.

Does Google Gemini API image generation work with Python for iterative artwork edits?▼

Yes, Gemini API image generation works with Python by utilizing the google-genai client and Pillow library to handle iterative artwork edits and produce both text and image outputs from your prompts.

Related Skills

Explore More Design & Creative Skills→
drshailesh88drshailesh88

nano-banana-pro

Generate or edit images via the Gemini 3 Pro Image API.

Community
Intermediate
SensLiaoSensLiao

brandkit

Generate brand-image kits with logos, identity systems, and visual guidelines.

Community
Advanced
iliagermaniliagerman
1

nano-banana-pro

Generate and edit images via the Gemini 3 Pro Image API.

Community
Intermediate
pmcdowallpmcdowall

stable-diffusion-image-generation

Generates AI images from text prompts using HuggingFace Diffusers pipelines.

Community
Advanced