ormus-illustrator

Generate images and videos via Gemini, Replicate, Midjourney, and PixelLab.

1|Updated Feb 2, 2026

Search Tags:#image generation #animation #gemini #midjourney #video generation #illustration #replicate

Ready to run

npx skills add https://github.com/HermeticOrmus/hermetic-claude --skill ormus-illustrator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ormus-illustrator
Source: https://github.com/HermeticOrmus/hermetic-claude/tree/main/claude/skills/ormus-illustrator
Command: npx skills add https://github.com/HermeticOrmus/hermetic-claude --skill ormus-illustrator

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the creation of AI-generated illustrations and videos, offering a multi-provider approach to visual content generation.

Core Features & Use Cases

Multi-Provider Support: Integrates with Gemini, Replicate, Midjourney, and PixelLab for diverse visual styles and capabilities.
Image & Video Generation: Supports text-to-image, image-to-video, and text-to-video generation.
Use Case: Generate a series of character concept art using Midjourney for a childlike style, then animate a still image of the best concept using Replicate's svd model for a short promotional video.

Quick Start

Use the ormus-illustrator skill to generate an image of a robot walking through a forest using the minimax model.

Frequently Asked Questions about ormus-illustrator

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

FAQPage Schema

How do I generate AI illustrations and videos using multiple providers like Midjourney and Gemini?▼

AI illustration and video generation is orchestrated by integrating Gemini, Replicate, Midjourney, and PixelLab. The skill handles text-to-image, image-to-video, and text-to-video tasks by routing requests to configurable models and styles across these specialized providers.

Can I animate a still image into a short video using Replicate?▼

Yes, you can animate a still image into a short video using Replicate's image-to-video capabilities. For example, you can generate character concept art and then use models like Replicate's svd to animate the best concept into a promotional video.

What is the Positive Loop workflow for refining AI image generation?▼

The Positive Loop workflow iteratively refines AI image generation results through Claude and user taste. This process allows you to progressively adjust and improve generated illustrations and videos until the visual output meets your desired quality and style.

Do I need Playwright to use this multi-provider text-to-video generation skill?▼

Yes, Playwright is a required dependency for this text-to-video and text-to-image generation skill. The environment must include Playwright to enable the orchestration of multiple specialized providers like Gemini and Midjourney.

Does this skill support text-to-image generation with childlike styles?▼

Yes, text-to-image generation supports childlike styles through Midjourney. You can generate character concept art series with specific visual aesthetics by configuring the available models and styles within the multi-provider framework.

What's the best way to orchestrate different models for text-to-image and image-to-video tasks?▼

The best way to orchestrate different models for text-to-image and image-to-video tasks is using a multi-provider approach. This skill coordinates Gemini, Replicate, Midjourney, and PixelLab to handle diverse visual styles and capabilities within a single workflow.