skills.rest
CristoVentures
CristoVenturesOFFICIAL
Explore all skills by this author →
GitHub

gemini-imagegen

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

2|Updated Apr 14, 2026
Search Tags:#editing#api#images#gemini#generate#style-transfer#reference-images
One-click install
npx skills add https://github.com/CristoVentures/LocalCents --skill gemini-imagegen-cristoventures
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/CristoVentures/LocalCents/tree/main/.agent/skills/gemini-imagegen
Command: npx skills add https://github.com/CristoVentures/LocalCents --skill gemini-imagegen-cristoventures

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini image generation and editing through the Gemini API enables creative workflows to produce or modify visuals directly from prompts, without manual tool-switching.

Core Features & Use Cases

  • Generate images from text prompts using Gemini.
  • Edit existing images with natural-language instructions and optional constraints (aspect ratio, size).
  • Compose multiple reference images into a single output, with multi-turn refinement support.

Quick Start

Provide a text prompt and Gemini will generate or edit an image according to your instructions.

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?▼

Generate and edit images using the Gemini API by providing text prompts and natural-language instructions. It streamlines creative workflows by producing visuals directly, supporting multi-turn refinement and optional constraints like aspect ratio.

Can I use reference images for style transfer and composition with Gemini?▼

Yes, style transfer and composition are supported by combining multiple reference images into a single output. You can provide visual inputs and apply natural-language instructions to guide the editing and style transfer process.

What do I need to set up before generating images with the Gemini API?▼

You need a valid GEMINI_API_KEY for authentication, along with the google-genai client library and Pillow for image handling. These dependencies enable the API connection and image processing required for generation.

How do I refine generated images without switching tools?▼

Refine generated images through multi-turn refinement by issuing follow-up natural-language instructions. This allows you to iteratively edit existing images and adjust constraints like size and aspect ratio directly within the workflow.

What are the limitations of using Gemini API for image generation?▼

Image generation and editing rely entirely on the Gemini API, requiring consistent API access and a valid GEMINI_API_KEY. Complex multi-turn refinement may be limited by API rate constraints or the model's interpretation of intricate reference images.

Does the Gemini API work with Pillow for image editing?▼

Yes, the Gemini API works with Pillow for image handling. While the google-genai library manages the API generation and editing calls, Pillow processes the image data locally to support the workflow.

Related Skills

Explore More Design & Creative Skills→
abhiunixabhiunix
1

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image via a local script.

Community
Intermediate
SJTU-IPADSSJTU-IPADS
7

image-utils

Automate deterministic image editing tasks on image collections with Pillow.

Official
Intermediate
kylesnowschwartzkylesnowschwartz
105

sc-gemini-imagegen

Automate image generation and editing using the Gemini API.

Community
Advanced
haitao2016haitao2016

neural-texture-synthesis

Implement Neural Style Transfer for artistic image generation in Lua.

Community
Advanced