skills.rest
open-octo
open-octoOFFICIAL
Explore all skills by this author →
GitHub

image-gen

Generate, source, or slice image files via AI providers and licensed services.

88|15|Updated May 25, 2026
Search Tags:#image generation#stock photos#ai art#image sourcing#batch manifests#image slicing
One-click install
npx skills add https://github.com/open-octo/octo-agent --skill image-gen-open-octo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/image-gen
Command: npx skills add https://github.com/open-octo/octo-agent --skill image-gen-open-octo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, numpy, google-genai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the complexity of acquiring production-ready image files by providing a unified workflow for AI generation, openly licensed web sourcing, and grid-sheet slicing.

Core Features & Use Cases

  • AI Image Generation: Create images through 14 provider backends, including OpenAI, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, and MiniMax.
  • Licensed Web Sourcing: Search and download suitable images from Openverse, Wikimedia, Pexels, and Pixabay while recording attribution details.
  • Batch and Post-Processing: Process image manifests with written-back status tracking, slice generated sheets into individual elements, and remove supported Gemini watermarks.
  • Use Case: When building a presentation, use this Skill to generate consistent illustrations, source licensed photographs, or create a single illustration sheet and split it into reusable visual elements.

Quick Start

Ask the image-gen skill to generate a specified image, source an openly licensed photograph, or slice a grid sheet into separate image files.

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I source openly licensed stock photos and record attribution details?▼

Sourcing openly licensed stock photos involves retrieving images from Openverse, Wikimedia, Pexels, and Pixabay while automatically recording attribution details. This provides compliant visual assets for design workflows and presentations.

Can I use multiple AI providers for image generation in a single workflow?▼

You can use multiple AI providers for image generation, including OpenAI, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, and MiniMax. Configuring the respective provider credentials beforehand enables this multi-backend functionality.

What is the best way to slice a generated image sheet into individual elements?▼

The best way to slice a generated image sheet into individual elements is using grid-sheet slicing functionality. This splits a single illustration sheet into separate image files, preparing reusable visual elements for your projects.

Do I need API keys to generate AI art or can I use keyless public sources?▼

You need configured provider credentials for AI art generation across backends like OpenAI or Stability. Alternatively, you can source openly licensed images from keyless public sources without requiring API keys.

How does batch image manifest processing track the status of downloaded images?▼

Batch image manifest processing tracks downloaded images through written-back status tracking. This records the acquisition state for each file in the manifest, ensuring reliable batch image production and post-processing.

Can I remove supported Gemini watermarks from generated AI images?▼

You can remove supported Gemini watermarks from generated AI images during the post-processing phase. This batch processing capability prepares clean visual assets for standalone use or delegated image production.

Related Skills

Explore More Design & Creative Skills→
lengo0951lengo0951

ai-multimodal

Process images, audio, and video with the Gemini API.

Community
Advanced
robikscuberobikscube

product-image-processor

Generate deterministic JSON processing manifests for batch product image workflows.

Community
Intermediate
mmmmmm786mngb-jpgmmmmmm786mngb-jpg

img-grid

Overlay a numbered grid on an image using Python and Pillow to measure column and row proportions.

Community
Intermediate
dangngocbinhdangngocbinh
2

video-resource-finder

Discover stock videos, images, music, and AI-generated assets via Pexels, Pixabay, Unsplash, Gemini, and DuckDuckGo.

Community
Advanced