skills.rest
barkleesanders
barkleesandersCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-imagegen

Generate and edit images using Google's Gemini 3 Pro model.

5|Updated Mar 27, 2026
Search Tags:#image generation#logo design#image editing#gemini#ai art#product mockups#image composition
One-click install
npx skills add https://github.com/barkleesanders/claude-code-starter --skill gemini-imagegen-barkleesanders
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/barkleesanders/claude-code-starter/tree/main/skills/gemini-imagegen
Command: npx skills add https://github.com/barkleesanders/claude-code-starter --skill gemini-imagegen-barkleesanders

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the barrier of needing professional graphic design tools or expertise to create, edit, and composite visual assets for projects like marketing materials, product mockups, logos, and social media content.

Core Features & Use Cases

  • Text-to-Image Generation: Create original images from detailed text prompts for logos, stickers, product mockups, or social media visuals.
  • Image Editing & Refinement: Modify existing images by adding elements, changing artistic styles, or adjusting details via simple conversational instructions.
  • Multi-Image Composition: Combine up to 14 reference images to create group photos, style transfers, or composite scenes for creative projects.
  • Iterative Refinement: Use multi-turn chat to progressively tweak generated or edited images until they match your exact vision.

Quick Start

Use the gemini-imagegen skill to generate a 16:9 2K product photo of a wireless headphone on a marble surface with soft three-point studio lighting.

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 without graphic design experience?▼

You can generate AI images from text prompts by providing detailed descriptions to the Gemini 3 Pro model, which creates original visuals for logos, stickers, and product mockups without requiring specialized graphic design tools.

Can I use multiple reference images for AI image composition and style transfer?▼

Yes, you can use multi-image composition to combine up to 14 reference images, allowing you to create composite scenes, group photos, and style transfers for creative projects and marketing workflows.

Do I need a GEMINI_API_KEY to edit images and apply style modifications?▼

Yes, a valid GEMINI_API_KEY is required. It interfaces with the google-genai library to modify existing images by adding elements, changing artistic styles, or adjusting details via conversational instructions.

What resolutions and aspect ratios does Gemini image generation support?▼

Gemini image generation supports resolutions up to 4K and aspect ratios ranging from 1:1 to 21:9, enabling the creation of high-quality visual assets for various content creation needs.

How do I iteratively refine generated images to match my exact vision?▼

You iteratively refine generated images by using multi-turn chat, progressively tweaking and editing the visual assets through simple conversational instructions until they match your specific design requirements.

What is the best way to create product mockups using AI image generation?▼

The best way to create product mockups is using text-to-image generation with detailed prompts specifying the product, surface, and lighting, such as requesting a 16:9 2K product photo with soft three-point studio lighting.

Related Skills

Explore More Design & Creative Skills→
iliagermaniliagerman
1

nano-banana-pro

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

Community
Intermediate
LoringtonianLoringtonian
12

nano-banana-pro

Generate images from text prompts and reference images using Gemini 3 Pro.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

image-generation

Generate images from text prompts via SDK or CLI with multiple output sizes.

Community
Intermediate
SignmanalSignmanal
1

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion and HuggingFace Diffusers.

Community
Advanced