Generative AI Masterclass (Early Access)

About Course

This course is in development, enrollment is paused as lessons and content are being added.

Unlock the full creative potential of generative AI in this hands-on masterclass, where you’ll explore an integrated workflow using ChatGPT for ideation, Pinokio for automated app orchestration, and ComfyUI as your visual node-based interface. Learn how to generate stunning images with Stable Diffusion, animate concepts through Text-to-3D tools, and push creative boundaries with fine-tuned LoRA (Low-Rank Adaptation) models—all seamlessly controlled inside a Pinokio-powered environment. Whether you’re building characters, designing cinematic worlds, or training personalized AI styles, this masterclass equips you with the tools and techniques to go from prompt to production with precision and unlimited creativity.

Once you have purchased the masterclass, you will be eligible for all future updates at no additional charge. For the first year there will be quarterly updates and tentative plans to add a minimum of one annual update per year through 2030.

Please Note: A tentative release date is scheduled for May 2025 for early access of introductory lessons. Remaining lessons will be completed through Fall of 2025. As lessons are added, the price of the course will gradually increase from $99.99 to $499.99. This is a tentative curriculum and subject to change without notice.

Prompt Engineering with ChatGPT
Automating Workflows with Pinokio
Visual Scripting in ComfyUI
Text to Image, Image to Image
Inpainting and Outpainting
Text-to-3D Techniques
Training Custom LoRA Models
Asset Optimization for VFX, Games & XR
Ethical & Legal Considerations in AI Art

Course Content

Course Overview

About the Generative AI Masterclass
About the Instructor

Foundations of Generative AI
Understand the history, technology, and terminology behind modern generative AI tools.

Prompting & Ideation with ChatGPT
Use ChatGPT as a creative partner to build effective prompts and generate ideas.

Introduction to ChatGPT
Overview of ChatGPT Models
What Makes a Great Prompt?
Using ChatGPT for Ideation and Scene Building
Creating a Custom Chatbot
Prompting for Characters, Worlds, and Narrative Scenes
Structuring Image Prompts for Style, Mood, and Composition
Building Prompt Variations for Batch Outputs
Prompt Drift & Iterative Distortion
Ethical Prompting and Dataset Awareness

Getting Started with ComfyUI
Set up your working environment and understand the node-based interface.

Text-to-Image Generation
Generate high-quality images using text prompts and prompt logic.

Image-to-Image & Visual Refinement
Modify, stylize, and evolve existing images using latent transformations.

Inpainting & Outpainting
Use masks to regenerate or expand parts of an image for creative iteration.

ControlNet for Guided Composition
Guide structure and layout with pose, depth, and edge maps.

IP-Adapter for Style Transfer & Image Conditioning
Use image prompts to guide AI generations visually, beyond text prompts.

Personalizing Style and Subject with LoRA
Customize your generations with LoRA models to control aesthetic, character identity, or thematic style.

Upscaling and Image Enhancement
Increase resolution and polish outputs for publishing or printing.

Batch Generation and Image Sequences
Automate generation of consistent series or high-volume outputs.

Video and Animation Concepts
Use generative images to drive early 3D design and asset creation.

Video-to-Video Generation
Use generative AI to transform, stylize, or reimagine video clips by processing them frame-by-frame through ComfyUI-compatible workflows.

Text & Image to 3D
Explore how to generate 3D assets from text and images using AI-based pipelines powered by ComfyUI, including Hunyuan3D workflows for multi-view 3D modeling.

3D Scanning, Custom LoRAs and Generative Rendering
Learn how to transform real-world 3D scan data and Gaussian splats into photorealistic images using ComfyUI and custom-trained LoRA models.

Synthetic Data & Computer Vision
Learn how to use generative AI techniques in ComfyUI to create synthetic datasets, augment training data, and simulate vision-based environments for ML applications.

Capstone Project – Project Quixote
Bring a scene from your screenplay to life using generative AI tools. This final project combines storytelling and visual development through ComfyUI and ChatGPT.

Introduction to Project Quixote
Creating the Project Quixote Chatbot
Collaborating with ChatGPT for Script Development
Creating Concept Art for Key Moments
Multi-Image to 3D Character Creation
Adjusting Character Poses & Composition
Building Storyboards with IP-Adapter, LoRA, and ControlNet
Generating Short Cinematic Animations or Mood Clips
Final Breakdown & Presentation

Student Ratings & Reviews

No Review Yet

About Course

What Will You Learn?

Course Content

Course Overview

About the Generative AI Masterclass

About the Instructor

Foundations of Generative AI Understand the history, technology, and terminology behind modern generative AI tools.

The Origins of AI: Neural Networks, GANs, and Milestones

The Rise of Transformers: GPT, BERT, and LLMs

Diffusion Models: Denoising, Latent Space, and Creativity

Key Terminology: Prompts, CFG, Seed, Latent Space, Samplers

Industry Use Cases: Games, Film, Design, Marketing

The Future of AI: Real-Time Gen, Agents, Ethics & Ownership

AI Model Collapse & Data Poisoning

Prompting & Ideation with ChatGPT Use ChatGPT as a creative partner to build effective prompts and generate ideas.

Introduction to ChatGPT

Overview of ChatGPT Models

What Makes a Great Prompt?

Using ChatGPT for Ideation and Scene Building

Creating a Custom Chatbot

Prompting for Characters, Worlds, and Narrative Scenes

Structuring Image Prompts for Style, Mood, and Composition

Building Prompt Variations for Batch Outputs

Prompt Drift & Iterative Distortion

Ethical Prompting and Dataset Awareness

Getting Started with ComfyUI Set up your working environment and understand the node-based interface.

What is Pinokio?

Installing ComfyUI with Pinokio

Understanding the Node-Based Graph Interface

Getting Started with Comfy Copilot

Downloading Checkpoints, VAEs, and LoRA Models

Saving, Reloading, and Organizing Workflows

Text-to-Image Generation Generate high-quality images using text prompts and prompt logic.

Creating Your First Text-to-Image Workflow

CFG, Steps, Seed, and Samplers Explained

Prompting for Style, Genre, Format, and Visual Language

Using LoRA for Specific Characters or Art Styles

Negative Prompts and Prompt Weighting

Stable Diffusion vs. Flux

Generating Stylized Concept Art with Flux

Flux Consistent Characters

Image-to-Image & Visual Refinement Modify, stylize, and evolve existing images using latent transformations.

Using Image-to-Image for Style or Scene Variation

Latent Strength, Noise, and Detail Preservation

Refining Faces, Objects, and Layout

Using I2I as Part of Iterative Creative Process

Inpainting & Outpainting Use masks to regenerate or expand parts of an image for creative iteration.

Introduction to Inpainting with Masks

Replacing Faces, Objects, or Background Elements

Outpainting for Canvas Expansion or Scene Worldbuilding

Best Practices for Seamless Visual Blending

ControlNet for Guided Composition Guide structure and layout with pose, depth, and edge maps.

What Is ControlNet and Why Use It?

Pose Guidance Using OpenPose and Scribble

Depth, Canny, and Edge Maps for Scene Structure

Combining Multiple ControlNets in One Graph

ControlNet + LoRA Workflows for Story-Driven Generation

IP-Adapter for Style Transfer & Image Conditioning Use image prompts to guide AI generations visually, beyond text prompts.

Intro to IP-Adapter in ComfyUI

Using Reference Images for Style or Character Transfer

Combining IP-Adapter with Text Prompts

Pose & Face Preservation with Image Prompts

Use Cases: Consistent Characters Across Scenes

Personalizing Style and Subject with LoRA Customize your generations with LoRA models to control aesthetic, character identity, or thematic style.

Understanding LoRA Models and How They Work

Loading and Merging Multiple LoRA Models

Adjusting LoRA Strength for Subtle or Bold Effects

Training Your Own LoRA with KohyaSS

Training Your Own LoRA with FluxGym

Refining LoRA results with XY Plots

Upscaling and Image Enhancement Increase resolution and polish outputs for publishing or printing.

Latent vs. Pixel-Based Upscaling

Using ESRGAN, 4x-UltraSharp, and Other Models

High-Res Fix Workflows and When to Use Them

Export Settings for Web, Print, or Compositing

Batch Generation and Image Sequences Automate generation of consistent series or high-volume outputs.

Batch Rendering with Loops and Queues

XY Plot: Iterating Style, Prompt, or LoRA

Maintaining Continuity Across Images

Use Cases: Comics, Storyboards, Product Design, and Variants