skills.rest
xiaoyu-ops
xiaoyu-opsCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

inno-figure-gen

Generate or edit PNG images via the Gemini 3 Pro Image API.

Updated Apr 1, 2026
Search Tags:#image-generation#gemini-3-pro#prompt-engineering#image-editing#ai-art#figure-generation#research-visuals
One-click install
npx skills add https://github.com/xiaoyu-ops/the_work_of_dedup --skill inno-figure-gen-xiaoyu-ops
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inno-figure-gen
Source: https://github.com/xiaoyu-ops/the_work_of_dedup/tree/main/.claude/skills/inno-figure-gen
Command: npx skills add https://github.com/xiaoyu-ops/the_work_of_dedup --skill inno-figure-gen-xiaoyu-ops

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

Generate/edit images for papers and presentations using Gemini 3 Pro Image, enabling rapid visual prototyping and figure creation without leaving the workspace.

Core Features & Use Cases

  • Supports text-to-image and image-to-image generation with resolutions of 1K, 2K, and 4K.
  • Accepts an optional --input-image for editing/modification, enabling iterative refinement of visuals.
  • Includes a straightforward command-line workflow (uv run ...) to produce and save PNG outputs for research artifacts such as figures and diagrams.
  • Workflow patterns include draft → iterate → final, with a simple default workflow to accelerate visualization tasks.

Quick Start

Run the script with a prompt and a filename to generate and save a PNG image

Frequently Asked Questions about inno-figure-gen

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

FAQPage Schema
How do I generate images for research papers using the Gemini 3 Pro API?▼

You generate research paper images by running the script with a text prompt and filename to invoke the Gemini 3 Pro Image API, which creates and saves a high-resolution PNG output directly to your specified path.

Can I edit an existing image to refine research visuals without regenerating it?▼

Yes, you can edit existing images by passing an optional input-image parameter to the script, enabling iterative image-to-image refinement of your research visuals using the Gemini 3 Pro API.

What resolutions are supported for AI art generation with this image-generation tool?▼

The image-generation tool supports resolutions of 1K, 2K, and 4K, allowing you to specify the exact output resolution needed for high-quality research figures and AI art prototypes.

Do I need a Gemini API key to create figures from prompts?▼

Yes, creating figures from prompts requires a valid Gemini API key to authenticate your requests with the Gemini 3 Pro Image API and successfully save the generated PNG outputs.

What is the best way to prototype high-resolution figures for presentations?▼

The best way to prototype high-resolution figures is using the draft, iterate, and final workflow pattern, leveraging prompt engineering and image-to-image editing to rapidly refine visuals for presentations.

Related Skills

Explore More Design & Creative Skills→
shane9coyshane9coy
1

nano-banana-pro

Generate and edit images via the Gemini 3 Pro Image API.

Community
Intermediate
jandan138jandan138

paper-write

Convert paper outlines into complete LaTeX manuscripts with sections, figures, and bibliography.

Community
Advanced
dalehurleydalehurley
2

image-tools

Resize, compress, convert, crop, and inspect images using Pillow.

Community
Intermediate
maragudkmaragudk
48

nanobanana

Generate and edit images via text prompts using the nanobanana CLI.

Official
Intermediate