Image Generator

Generate and edit images via Gemini's image-generation API.

5|3|Updated Nov 5, 2025

Search Tags:#image-generation #mockups #text-to-image #image-editing #logos #AI-art #inpainting

Ready to run

npx skills add https://github.com/chekos/bns-marketplace --skill image-generator-chekos

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Image Generator
Source: https://github.com/chekos/bns-marketplace/tree/main/tdd-design/skills/image-generation
Command: npx skills add https://github.com/chekos/bns-marketplace --skill image-generator-chekos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines visual content creation by generating and editing images using Gemini's advanced image model, reducing manual design workloads and speeding up iteration.

Core Features & Use Cases

Text-to-Image Generation: Produce high-quality visuals from descriptive prompts for logos, mockups, marketing assets, or social media.
Image Editing & Inpainting: Modify existing images by adding/removing elements, changing colors, or applying stylistic edits.
Multi-Input Composition & Responsive Output: Combine inputs from multiple sources and generate outputs in configurable aspect ratios and resolutions to fit different channels.

Quick Start

Describe the image you want and, optionally, provide input images to guide edits. Run the image generator with your prompt to receive an initial result, then iterate by refining prompts or edits.

Frequently Asked Questions about Image Generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate images from text descriptions using Gemini AI?▼

Text-to-image generation works by sending your descriptive prompt to the Gemini image-generation API using the gemini-3-pro-image-preview model. It produces high-quality visuals suitable for logos, mockups, or marketing assets.

Can I edit existing images and do inpainting with Gemini AI?▼

Yes, you can edit existing images and perform inpainting by providing input images alongside modification prompts. The tool interfaces with the Gemini API to add, remove elements, change colors, or apply stylistic edits to your visuals.

Do I need a GEMINI_API_KEY to run text-to-image generation?▼

Yes, you need a GEMINI_API_KEY set in your environment to run this image generator. This key is required to authenticate and interface with the Gemini image-generation API for processing prompts and input images.

Can I combine multiple input images to create a single composition?▼

Yes, multi-input composition allows you to combine inputs from multiple sources into a single generated visual. You provide multiple input images alongside your prompt, and the tool processes them to produce a unified composition.

What are the limitations of using the gemini-3-pro-image-preview model for AI art?▼

A key limitation is its strict dependency on the gemini-3-pro-image-preview model and a valid GEMINI_API_KEY environment variable. Output quality for AI art or mockups depends entirely on prompt specificity and the model's current capabilities.