skills.rest
sylvanding
sylvandingCOMMUNITY
Explore all skills by this author →
Website𝕏@sylvandingGitHub

gemini-imagegen

Generate, edit, and compose images via the Gemini API.

9|Updated Mar 9, 2026
Search Tags:#image generation#logo design#image editing#gemini#ai art#product mockup#multi-turn refinement
One-click install
npx skills add https://github.com/sylvanding/omelette --skill gemini-imagegen-sylvanding
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/sylvanding/omelette/tree/main/.claude/skills/gemini-imagegen
Command: npx skills add https://github.com/sylvanding/omelette --skill gemini-imagegen-sylvanding

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of working with the Gemini API for image tasks, eliminating the need to write boilerplate code for API calls, handle response parsing, or troubleshoot common format issues like mismatched image file extensions.

Core Features & Use Cases

  • Text-to-Image Generation: Create custom images from text prompts with control over resolution and aspect ratio, ideal for marketing assets, social media content, and concept art.
  • Image Editing & Composition: Modify existing images or combine up to 14 reference images into new compositions, perfect for product mockups, photo retouching, and creative visual projects.
  • Iterative Multi-Turn Refinement: Chat with the model to progressively tweak images through conversational feedback, great for logo design, visual prototyping, and fine-tuning creative outputs.
  • Use Case: A small business owner can generate product mockups for their online store, edit product photos to match brand aesthetics, and refine designs through simple chat commands without hiring a professional designer.

Quick Start

Use the gemini-imagegen skill to generate a 16:9 widescreen product photo of a wireless coffee maker on a marble countertop with soft studio lighting and save it as product_shot.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 can generate AI images from text prompts using the Gemini API by specifying desired resolution and aspect ratio. This handles API authentication and response parsing automatically, allowing rapid creation of visual assets without manual boilerplate code.

Can I combine multiple reference images into a single composition with Gemini?▼

Yes, you can combine up to 14 reference images into new compositions with Gemini. This is ideal for creating product mockups, executing photo retouching, and generating creative visual projects directly through API calls.

How does multi-turn refinement work for AI image editing?▼

Multi-turn refinement works for AI image editing by maintaining chat sessions with the model to progressively tweak images. You provide conversational feedback to fine-tune creative outputs, which is especially useful for logo design and iterative visual prototyping.

Do I need to manually normalize image file extensions when using the Gemini API?▼

No, you do not need to manually normalize image file extensions when using the Gemini API. The process automatically handles JPEG format normalization and resolves common mismatched file extension issues out of the box.

What are the limitations of using Gemini for text-to-image generation?▼

Limitations of using Gemini for text-to-image generation include dependency on the google-genai and Pillow libraries. While it streamlines asset creation and mockup design, outputs are normalized to JPEG format, which may restrict specific transparency requirements.

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
yikartyikart
24.9k

managing-content

Organize media files, drafts, and content collections for publishing workflows.

Official
Intermediate
bhushanofficial69-specbhushanofficial69-spec

photo-editor

Apply programmable resize, crop, filter, and watermark operations to images.

Community
Intermediate
RedWoodOGRedWoodOG
174

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion and diffusers pipelines.

Community
Advanced