skills.rest
All-The-Vibes
All-The-VibesOFFICIAL
Explore all skills by this author →
GitHub

gemini-imagegen

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

50|14|Updated Mar 11, 2026
Search Tags:#composition#gemini#image-generation#generate#image-editing#reference-images#ai-art
One-click install
npx skills add https://github.com/All-The-Vibes/ATV-StarterKit --skill gemini-imagegen-all-the-vibes
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/All-The-Vibes/ATV-StarterKit/tree/main/.github/skills/gemini-imagegen
Command: npx skills add https://github.com/All-The-Vibes/ATV-StarterKit --skill gemini-imagegen-all-the-vibes

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automates image generation and editing tasks by interfacing with the Gemini API to create or modify visuals from textual prompts, reducing manual design workload.

Core Features & Use Cases

  • Text-to-image generation using Gemini models (gemini-2.5-flash-image and gemini-3-pro-image-preview) to produce high-quality visuals from prompts.
  • Image editing and refinement by supplying an input image and a descriptive instruction, enabling iterative improvements.
  • Composition and multi-reference workflows via scripts (compose_images.py and related tooling) to combine multiple references into a single output.

Quick Start

Run the Gemini-imagegen scripts to generate or edit images from prompts using your Gemini API key.

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?▼

To generate images from text prompts using the Gemini API, you supply a descriptive text prompt and your GEMINI_API_KEY to a designated model like gemini-2.5-flash-image. The API then processes the text modality to produce high-quality visual outputs.

Can I edit an existing image by providing a text instruction to Gemini?▼

Yes, you can edit an existing image by supplying the input image alongside a descriptive text instruction to the Gemini API. This enables iterative image refinement and targeted modifications without needing to regenerate the visual from scratch.

How do I combine multiple reference images into a single composition?▼

You can combine multiple reference images into a single composition by utilizing specific scripts like compose_images.py within the Gemini image generation workflow. This allows the API to synthesize elements from several inputs into one cohesive output.

Do I need a GEMINI_API_KEY to use Gemini image generation models?▼

Yes, a valid GEMINI_API_KEY is strictly required to authenticate and use the Gemini API for any image generation or editing tasks. You must configure this key in your environment before executing the text-to-image scripts.

What Gemini models are available for AI image generation and editing?▼

The available Gemini models for AI image generation and editing include gemini-2.5-flash-image and gemini-3-pro-image-preview. Selecting between these models allows you to balance processing speed and output preview capabilities for your visual workflows.

Can I specify aspect ratio and size when generating images with Gemini?▼

Yes, you can specify aspect ratio and size during image generation by passing an optional image_config parameter to the Gemini API. This configuration ensures the generated visual matches your required formatting dimensions for logos or mockups.

Related Skills

Explore More Design & Creative Skills→
aryaxtaryaxt

generate-image

Generate single or batch images using Google Gemini's image generation API.

Community
Intermediate
ankitjh4ankitjh4

generate-custom-qr-code

Generate QR codes from URLs with optional center image overlays.

Community
Basic
tdiminotdimino
41

nano-banana-pro

Generate and edit images via Google's Nano Banana Pro API.

Community
Advanced
Brilly-BohyunBrilly-Bohyun

comfyui

Automate image, video, and audio generation with ComfyUI and AI models.

Community
Advanced