Image-to-image

Checkpoint model 2

Extension for installing models

CLIP Skip

Merging two models

Model file formats

Other model types

Quiz - Checkpoint model 2

Prompt building 2

Introduction - Prompt building 2

Effect of checkpoint models

Quizzes - Prompt building 2

AUTOMATIC1111 extensions

Introudction - AUTOMATIC1111 extensions

Installing extensions

Civitai Helper extension

Infinite Browser extension

LoRA

Introduction - LoRA models

What is LoRA?

How does LoRA work?

How to find and use LoRA?

Some useful LoRA models

Exercise - LoRA

Quiz - LoRA

Textual Inversion

Introduction - Textual Inversion

What is textual inversion?

How to install textual inversion

How to use textual inversion

Some useful textual inversions

Exercises - Textual Inversion

Textual inversions are keywords

Quiz - Textual inversion

Hypernetwork

Introduction - Hypernetwork

What is Hypernetwork?

How to find and install hypernetworks?

How to use hypernetworks?

Some hypernetwork examples

Quiz - Hypernetwork

AI Upscalers

Introduction - Upscalers

What is an AI upscaler?

How does an AI upscaler work?

Use an AI upscaler

AI upscalers overview

Install additional upscalers

Quiz - AI upscalers

How Stable Diffusion work 2

Introduction - How Stable Diffusion work 2

Quiz - How Stable Diffusion work 2

ControlNet 1

Introduction - ControlNet 1

What is ControlNet?

Installing ControlNet extension

Updating ControlNet extension

A simple usage example

Preprocessors and models

ControlNet Openpose

ControlNet Canny

ControlNet IP adapter

Quiz - ControlNet 1

An End-to-end workflow 2

Introduction to End-to-end workflow 2

Step 1: Build a base prompt

Step 2: Select a model

Step 3: Refine the prompt

Step 4: Fix defects with inpainting

Step 5: Enlarge image with AI upscaler

Exercise - End-to-end workflow 2

Quiz – How Stable Diffusion work 2

What mechanism allow the text prompt controls the image generation? *

VAE

U-Net

Conditioning

Diffusion

Which part of the model converts the text prompt to a numerical representation? *

Tokenizer

Text transformer

U-Net

VAE

What does CLIP do? *

Denoise the image.

Convert the image from the pixel space to the latent space.

Convert the image from the latent space to the pixel space.

Convert the text prompt to the embeddings.

What is a noise schedule? *

The number of sampling steps.

The target amount of noise at each step.

The total amount of noise added in each generation.

The noise injected by the attention layers.

What's the effect of increasing the CFG scale? *

Higher quality images.

Requires fewer sampling steps.

A higher initial amount of noise is injected.

The images follow the prompt more closely.

What does the SDXL model consist of? *

The base model

The base and enhancer models

The base and refiner models

The base and finisher models

Stable Diffusion - Level 2

Quiz – How Stable Diffusion work 2