skills.rest
maystudios
maystudiosCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-image-gen

Automate Chrome interactions to generate and download images from Google Gemini.

15|1|Updated Apr 16, 2026
Search Tags:#gemini#image-generation#generate#prompt-engineering#reference-images#inpainting#chrome-automation
One-click install
npx skills add https://github.com/maystudios/claude-skills --skill gemini-image-gen-maystudios
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-image-gen
Source: https://github.com/maystudios/claude-skills/tree/main/gemini-image-gen
Command: npx skills add https://github.com/maystudios/claude-skills --skill gemini-image-gen-maystudios

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates the manual, error-prone process of generating, downloading, and saving images from Google Gemini's web interface by orchestrating Chrome browser actions and structured prompts so users can produce consistent, high-quality assets without repetitive UI work.

Core Features & Use Cases

  • End-to-end browser automation: Opens tabs, enables Gemini image generation, uploads up to 14 reference images, submits enhanced prompts, waits for renders, and downloads outputs.
  • Flexible prompt and output control: Supports resolution selection (0.5K–4K), many aspect ratios, style transfer, inpainting, text rendering, and prompt-enhancement guidelines for photographic and cinematic results.
  • Robust file handling and error guidance: Locates the most recent download, moves files to a specified destination, and includes troubleshooting steps for navigation, generation failures, and missing downloads.
  • Use Case: Produce a 4K character concept with three reference images, refine with inpainting, and automatically place the final PNG into a project's asset folder.

Quick Start

Generate a 4K image in Gemini from these reference images and save the final PNG to /project/assets.

Frequently Asked Questions about gemini-image-gen

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

FAQPage Schema
How do I automate image generation in Google Gemini?▼

Automate Google Gemini image generation by orchestrating Chrome browser interactions to submit prompts, upload reference images, and download output files. This handles tab navigation, prompt submission, render waiting, and file saving automatically.

How many reference images can I upload for Gemini style transfer and inpainting?▼

You can upload up to 14 reference images for Gemini style transfer and inpainting tasks. The automation handles the browser upload process, enabling detailed concept art creation and targeted image modifications using multiple visual inputs.

Can I control aspect ratio and resolution for images generated through Gemini browser automation?▼

Yes, you can specify explicit resolutions ranging from 0.5K to 4K and select from many aspect ratios for generated images. The automation applies these parameters during the prompt construction phase to ensure outputs match your project requirements.

How do I move downloaded Gemini images to a specific project directory?▼

Move downloaded Gemini images to a specific project directory by specifying a destination path in the automation. The system locates the most recent download, verifies the file, and automatically moves the final PNG to your desired folder.

What should I do when Google Gemini image generation fails or the download is missing?▼

When Google Gemini image generation fails or downloads are missing, follow the built-in troubleshooting steps for navigation errors and generation failures. The automation includes robust file handling to verify downloads and retry rendering steps if needed.

Related Skills

Explore More Design & Creative Skills→
sunyonghuansunyonghuan
46

transfer

Transfer files between local and server locations with overwrite safety.

Community
Intermediate
WynterJonesWynterJones
5

image-processing

Resize, convert, crop, and optimize images using ImageMagick commands.

Community
Intermediate
bahayonghangbahayonghang
16

gemini-image

Generate images from text prompts or reference images via the Gemini API.

Community
Basic
math-incmath-inc
1.2k

stable-diffusion-image-generation

Generate images from natural language prompts using Stable Diffusion models.

Official
Advanced