skills.rest
8b-is
8b-isOFFICIAL
Explore all skills by this author →
WebsiteGitHub

gemini-imagegen

Generate and edit images via the Gemini API in Python.

Updated Jan 16, 2026
Search Tags:#editing#image#AI#Gemini#generate#mockups
One-click install
npx skills add https://github.com/8b-is/8b-is-mp --skill gemini-imagegen-8b-is
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/8b-is/8b-is-mp/tree/main/plugins/compound-engineering/skills/gemini-imagegen
Command: npx skills add https://github.com/8b-is/8b-is-mp --skill gemini-imagegen-8b-is

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill streamlines the process of generating and editing images by interfacing with Gemini API, enabling rapid visual iteration for designers, marketers, and product teams.

Core Features & Use Cases

  • Generate images from text prompts (text-to-image) using Gemini.
  • Edit existing images with natural language instructions and iterative refinement.
  • Compose and refine visuals from multiple reference images for logos, product mockups, stickers, and branding assets.
  • Real-world use: A designer can rapidly prototype logo variations by prompts and refinements.

Quick Start

Run the provided scripts to generate or edit images. Example:

  • Generate: python scripts/generate_image.py "A futuristic logo for Acme" acme_logo.png --model gemini-3-pro-image-preview --aspect 1:1
  • Edit: python scripts/edit_image.py input.png "Make the image more vibrant and add a gold tint" edited.png --model gemini-3-pro-image-preview

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 from text prompts using the Gemini API in Python?▼

Generate images from text prompts by running the provided Python scripts with the Gemini API, which creates visual assets like logos and mockups from your descriptive text input. You can specify the model and aspect ratio directly via command line arguments.

Can I edit existing images with natural language instructions in Python?▼

Yes, you can edit existing images with natural language instructions by running the edit script, which applies your text-based modifications like adding color tints to the input image and saves the refined output locally.

Do I need the Pillow library to process generated images locally?▼

Yes, the Pillow library is required alongside google-genai to handle local image processing, enabling you to manage file inputs and outputs effectively when generating or editing visuals in your Python environment.

What is the best way to rapidly prototype logo variations for product branding?▼

The best way to prototype logo variations is using iterative text-to-image generation and refinement, allowing designers to compose and refine visuals from multiple reference images through sequential natural language prompts.

Does this image generation workflow support composing visuals from multiple reference images?▼

Yes, the workflow supports composing and refining visuals from multiple reference images, enabling you to merge and iterate on existing assets for branding materials, stickers, and product mockups directly through API calls.

Related Skills

Explore More Design & Creative Skills→
resultanyildiziresultanyildizi
4

nano-banana-pro

Generate and edit images via Google's Gemini 3 Pro Image API.

Community
Intermediate
jhlee0409jhlee0409

prompt-strategy

Develop and optimize AI prompt strategies for code generation across multiple models.

Community
Advanced
Benmore-StudioBenmore-Studio
1

nano_banana

Generate and edit images via the Gemini 2.5 flash-image model.

Official
Intermediate
ChenYCLChenYCL

canvas-design

Generate posters, flyers, and infographics in PNG and PDF formats using Python graphics libraries.

Community
Intermediate