skills.rest
proyecto26
proyecto26OFFICIAL
Explore all skills by this author →
Website𝕏@proyecto_26GitHub

genimg-gemini-web

Generate images and text from prompts using Gemini Web.

35|2|Updated Feb 2, 2026
Search Tags:#automation#image-generation#multi-turn#prompt-based#reference-images#gemini-web
One-click install
npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill genimg-gemini-web
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: genimg-gemini-web
Source: https://github.com/proyecto26/sherlock-ai-plugin/tree/main/skills/genimg-gemini-web
Command: npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill genimg-gemini-web

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables generating images (and text) using Gemini Web from prompts, with optional reference images and session persistence to support multi-turn interactions.

Core Features & Use Cases

  • Image generation: convert prompts into downloadable images and save locally.
  • Text generation: produce text content and captions alongside images.
  • Reference image support: upload and reuse reference images to guide generation.
  • Multi-turn conversations: persist chat context across requests for consistent outputs.
  • Video generation (experimental): request video outputs when Gemini supports it.

Quick Start

Use the Gemini Web skill to generate an image: npx -y bun scripts/main.ts --prompt "A serene mountainscape" --image mountains.png

Frequently Asked Questions about genimg-gemini-web

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

FAQPage Schema
How do I generate images from prompts using Gemini Web?▼

To generate images from prompts using Gemini Web, you run the client script with a text prompt, which automates the browser session to produce and download the requested images locally.

Can I use reference images to guide Gemini Web image generation?▼

Yes, you can upload and reuse reference images to guide Gemini Web image generation, allowing the model to match existing visual styles and contextual details for your marketing or presentation assets.

How do I automate multi-turn image generation with persistent session state?▼

Automated multi-turn image generation maintains session state via cookie handling and client-side executor logic, allowing continuous chat interactions that build upon previous visual outputs without losing context.

Does Gemini Web automation support generating text captions alongside images?▼

Gemini Web automation supports generating text content and captions alongside images, enabling complete content creation workflows where visual assets and descriptive text are produced simultaneously.

What are the limitations of using browser automation for Gemini Web image generation?▼

Limitations of browser automation for Gemini Web include dependency on active cookie-based sessions, experimental status for video outputs, and the need for local file management when downloading generated images.

Related Skills

Explore More Design & Creative Skills→
SpaceZephyrSpaceZephyr
333

baoyu-danger-gemini-web

Generate Gemini Web text, image, and vision outputs from prompts and reference files.

Community
Advanced
AcosmiAcosmi
6

image

Generate, edit, analyze, and convert images via configured vision models.

Community
Advanced
augustsclaugustscl
2

baoyu-danger-gemini-web

Generate text and images via the reverse-engineered Gemini Web API.

Community
Advanced
ideaccoideacco
13

baoyu-post-to-wechat

Automate publishing Markdown or HTML articles to WeChat Official Accounts.

Community
Advanced