StretchLearn Course

Create and customize your own AI art with open-source Stable Diffusion

From first install to LoRA and ControlNet — the practical workflow in ComfyUI, Automatic1111, and Leonardo.ai.

Beginner10 hr 25 minSelf PacedRegistered

Course Overview

What this course is designed to develop

This course teaches the practical open-source image-generation workflow that artists and creators actually use, built around Stable Diffusion 1.5, SDXL, and SD3.5 models running in Automatic1111, ComfyUI, or the hosted Leonardo.ai. You will write structured prompts, tune samplers and CFG, swap checkpoints and VAEs, stack LoRA adapters, and pin composition with ControlNet. Every module uses named models, real numeric settings, and worked examples you can reproduce on your own machine or in the cloud.

Learning Outcomes

What the learner should be able to understand, build, or execute.

Install and run Stable Diffusion locally via Automatic1111 or ComfyUI, or generate in the cloud with Leonardo.ai

Choose the right base model — SD 1.5, SDXL, or SD3.5 — and load checkpoints, VAEs, and embeddings correctly

Write structured positive and negative prompts and tune steps, CFG scale, sampler, and seed for repeatable results

Stack and weight LoRA adapters to apply specific styles, characters, and subjects on top of a base model

Control composition, pose, and depth precisely using ControlNet preprocessors such as Canny, Depth, and OpenPose

Upscale, fix faces and hands, run image-to-image and inpainting, and export production-ready files

Curriculum Preview

Inside the curriculum: a structured path from fundamentals to execution.

Preview the course structure, see how the modules build on one another, and understand the path this program is designed to take you through.

Module 1

Module 1: Getting Started with Stable Diffusion

Understand what Stable Diffusion is, how the open-source ecosystem fits together, and how to get a working generator running locally or in the cloud.

3 lessons

What Stable Diffusion Is and Why It Is OpenContent · 45 min

Preview Enabled

Choosing Your Runtime: Local vs Cloud vs HostedContent · 50 min

LMS Access

Installing and Launching Your First GeneratorContent · 55 min

LMS Access

Module 2

Module 2: Prompts, Models, and Core Settings

Turn random luck into repeatable results by mastering prompt structure, base-model choice, and the handful of settings that actually change your output.

3 lessons

Writing Prompts That WorkContent · 50 min

LMS Access

Choosing a Base Model: 1.5, SDXL, or SD3.5Content · 50 min

LMS Access

Steps, CFG, Samplers, Seeds, and VAEContent · 55 min

LMS Access

Module 3

Module 3: Customizing with LoRA, Embeddings, and ControlNet

Move from random generation to precise control by adding style and subject with LoRA and pinning composition with ControlNet.

3 lessons

Using and Weighting LoRA AdaptersContent · 55 min

LMS Access

Embeddings and Subtle Quality ToolsContent · 45 min

LMS Access

Precise Control with ControlNetContent · 60 min

LMS Access

Module 4

Module 4: Refining, Scaling, and Production Workflows

Fix the common flaws, upscale to high resolution, build repeatable pipelines in ComfyUI, and handle rights and export for real use.

3 lessons

Fixing Faces and Hands, Inpainting, and Img2ImgContent · 55 min

LMS Access

Upscaling to High ResolutionContent · 50 min

LMS Access

ComfyUI Pipelines, Rights, and ExportContent · 55 min

LMS Access

Built for Application

A complete learning path, not a one-off inspiration hit.

This program is designed around progression: focused lessons, structured modules, applied resources, assessments, and a course rhythm that turns information into usable capability.

Stable DiffusionComfyUIAutomatic1111SDXLLoRAControlNetLeonardo.aiAI art