skills.rest
PederHP
PederHPCOMMUNITY
Explore all skills by this author →
GitHub

image-gen

Generate and edit images across Gemini, OpenAI, BFL FLUX, and Poe.

1|Updated Dec 24, 2025
Search Tags:#editing#CLI#AI#image-generation#multi-provider#prompt
One-click install
npx skills add https://github.com/PederHP/image-gen-cli --skill image-gen-pederhp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/PederHP/image-gen-cli/tree/main/image-gen
Command: npx skills add https://github.com/PederHP/image-gen-cli --skill image-gen-pederhp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires dotnet, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill consolidates image generation and editing across multiple AI providers, simplifying access to high-quality visuals from a single interface.

Core Features & Use Cases

  • Multi-provider support: Gemini, OpenAI, BFL FLUX, and Poe for flexible model access.
  • Prompt-based image creation and edit workflows: generate new images from descriptions and modify existing ones with instructions.
  • Batch and variation generation: produce multiple image variations in a single run to compare concepts.

Quick Start

Run: image-gen "A sunset over mountains with a tranquil lake" to generate a single image using the default Gemini provider.

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I generate AI images from multiple providers using a single CLI?▼

To generate AI images from multiple providers, you run a single CLI command with your text prompt, which automates requests to Gemini, OpenAI, BFL FLUX, and Poe to produce the desired visual output.

Can I edit existing AI images with prompt instructions?▼

Yes, you can edit existing images with prompt instructions by passing the image file and modification text to the CLI, which processes the edit request across supported AI generation providers.

Do I need a .NET runtime to run AI image generation workflows?▼

Yes, you need the .NET 10.0 runtime installed to execute the image generation workflows, as the skill scripts require this specific environment to run properly and process provider API calls.

What is the best way to generate multiple image variations for prototyping?▼

The best way to generate multiple image variations for prototyping is using the batch generation feature, which produces multiple concept outputs in a single run directly from your text prompt.

How do I manage API keys for different image generation models?▼

You manage API keys for image generation models by configuring environment-based variables or passing CLI flags, allowing the workflow to authenticate securely across Gemini, OpenAI, BFL FLUX, and Poe.

Can I specify aspect ratio and resolution options when creating AI images?▼

Yes, you can specify aspect ratio and resolution options when creating AI images, as the CLI supports these parameters to customize the output dimensions for your generation and edit workflows.

Related Skills

Explore More Design & Creative Skills→
het8802het8802
3

bfl-api

Generate and edit images using BFL FLUX API endpoints.

Community
Advanced
kienhaminhkienhaminh

gemini-image-gen

Generate and edit images from text prompts using Gemini 2.5 Flash Image.

Community
Advanced
resultanyildiziresultanyildizi
4

nano-banana-pro

Generate and edit images via Google's Gemini 3 Pro Image API.

Community
Intermediate
chekoschekos
5

Image Generator

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

Community
Intermediate