skills.rest
biwakonbu
biwakonbuCOMMUNITY
Explore all skills by this author →
Website𝕏@biwakonbuGitHub

image-generation

Generate images from prompts using the Gemini CLI and gemini-3-pro-image-preview model.

Updated Jan 8, 2026
Search Tags:#CLI#images#generate#prompt-based#reference images#Gemini Nano Banana Pro
One-click install
npx skills add https://github.com/biwakonbu/cc-plugins --skill image-generation-biwakonbu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/biwakonbu/cc-plugins/tree/main/plugins/nano-banana-image/skills/image-generation
Command: npx skills add https://github.com/biwakonbu/cc-plugins --skill image-generation-biwakonbu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables users to generate AI-driven images from textual prompts using Gemini Nano Banana Pro, simplifying illustration creation and image edits without requiring manual drawing.

Core Features & Use Cases

  • Prompt-based image generation using gemini-3-pro-image-preview to produce high-quality visuals.
  • Configurable output: supports 1K, 2K, or 4K resolutions and multiple aspect ratios (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9).
  • Reference-assisted editing: leverage up to 14 reference images to guide style or content.
  • Usage scenarios: concept art, illustrations, product visuals, or quick visuals from a short prompt in creative work.

Quick Start

  1. Analyze the user request to extract:
    • prompt, resolution, aspect ratio, and reference images.
  2. Build a detailed, style-aware prompt (prefer English) for Gemini.
  3. Generate with Gemini CLI: gemini --yolo --model gemini-3-pro-image-preview "Generate an image: {Prompt}"
  4. Check the output path and share results with the user.
  5. Optional: specify options inline, for example: gemini --yolo --model gemini-3-pro-image-preview "Generate an image with 16:9 aspect ratio at 2K resolution: {Prompt}"
  6. If using references: gemini --yolo --model gemini-3-pro-image-preview "Edit this image: {Edit instruction}" --files {image_path}

Note: Gemini CLI must be installed, API key configured, and generated images will include a SynthID watermark. Inappropriate content generation is rejected.

Frequently Asked Questions about image-generation

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

FAQPage Schema
How do I generate images from textual prompts using the Gemini CLI?▼

To generate images from textual prompts, use the Gemini CLI with the gemini-3-pro-image-preview model to execute prompt-based commands and output high-quality visual files. You must include your prompt in the command execution.

Can I use reference images to guide AI image edits?▼

Yes, you can use reference images to guide AI image edits by passing up to 14 image files directly to the Gemini CLI command using the --files flag along with your specific edit instructions.

Do I need an API key to generate images with Gemini Nano Banana Pro?▼

Yes, you need an API key to generate images with Gemini Nano Banana Pro, alongside a properly installed Gemini CLI environment to authorize requests and run the required gemini-3-pro-image-preview model.

What resolutions and aspect ratios are supported for prompt-based image generation?▼

Prompt-based image generation supports 1K, 2K, or 4K resolutions and multiple aspect ratios including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9 for configurable output formats.

Are there limitations on generating inappropriate content with Gemini image generation?▼

Yes, a major limitation is that inappropriate content generation is strictly rejected by the Gemini model, and all successfully generated output images will include a mandatory SynthID watermark.

Related Skills

Explore More Design & Creative Skills→
robomotioniorobomotionio
2

gemini-ai

Automate Gemini text generation, image analysis, and embeddings via the robomotion googlegemini CLI.

Official
Advanced
safzanpiranisafzanpirani
1

reverse-synthid

Remove watermarks from AI-generated images using the reverse-SynthID project.

Community
Advanced
jau123jau123
1.7k

AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI

Generate images and videos from text prompts and reference images.

Community
Advanced
SheshiyerSheshiyer
4

flux-image

Generate images from FLUX models via the inference.sh CLI.

Community
Intermediate