Master Stable Diffusion with Python: AI Images & Video

Name: Master Stable Diffusion with Python: AI Images & Video
Rating: 4.4 (191 reviews)

ControlNet, DreamBooth, LoRA, Diffusers, AnimateDiff, AUTOMATIC1111

Created byRiad Almadani • 70,000+ Students

Last updated 7/2026

English

English [Auto],Korean [Auto],

What you'll learn

learning about diffusion models
practical applications of AI-generated images
students will have the knowledge and skills to build their own machine that can generate realistic images
How to generate your own art using AI
learning about diffusers package
learning about Automatic1111 and how to use it
How to understand and implement research papers
How to build a system to convert your video into animation
How to use diffusers library
How to convert your audio to video using AI

Course content

12 sections • 100 lectures • 21h 17m total length

What you will learn in this course ?2:28
what is stable diffusion ?11:29
Where to find the codes ?2:24
How does stable diffusion model work?1:19
what is gaussian distribution?7:39
What is Markove chain ?4:12
What is Forward diffusion ?7:32
What is Reparameterization Trick ?11:44
What is variance schedule ?6:37
Linear variance schedule Vs cosine-based variance schedule4:23
What is Reverse diffusion ?10:21
How can we train our network part1 ?3:19
How can we train our network part2 ?10:54
How can we train our network part3 ?1:56
How can we train our network part4 ?2:54
Stable Diffusion Inference4:04
What is U network ?9:47
How to create Unconditional diffusion model ?4:49
What is positional embedding ?10:58
How to create Conditional diffusion model ?9:18

How to build and train unconditional diffusion model from scratch ?31:14
How to use any pretrained diffusion model from Hugging Face Hub ?13:22
How can we do Inpaint using our diffusion model?11:57
How to implement Repaint algorithm? python code33:30
How to speed up your diffusion model ?14:55
DDIM vs DDPM python code16:57
DDIM and out of domain images7:30
DDIM and out of domain images python code23:47
What is style transfer ?24:16
style transfer python code44:10

What is stable diffusion ?6:36
stable diffusion part 1 python code23:20
stable diffusion part 2 python code12:47
Fine-tuning your stable diffusion model using DreamBooth notebook part119:29
What is Mixed Precision ?8:41
Fine-tuning your stable diffusion model using DreamBooth notebook part215:21
What is ControlNet ?16:36
ControlNet with stable diffusion model using diffusers19:45
Inpainting with stable diffusion model7:05

Optical flow using FlowNet12:01
Optical flow using GMFlow15:30
Optical flow using GMFlow ?python code40:07
How to convert your video into frames ?python code22:15
How to extract the latents ? python code18:54
How to find the canny inputs and the latents for each key-frame ? python code25:43
How to generate new key-frames using sd model with control net ? python code21:20
What is cross frame-attention ?14:18
How to do cross-frame attention part1 ? python code15:02
How to do cross-frame attention part2 ? python code19:02
How to make your generated key-frames sharing the same textures ?14:23
Shape-aware module python code23:28
Pixel-Aware module13:22
Pixel-Aware module python code38:20
How to do keyframes to animation?4:29

what is diffusers library ?1:21
how to create a pipeline object and how to use it ?17:27
how these pipelines work ?17:11
How to use the same diffusion model to do different tasks ?4:35
How to select the best scheduler ?5:07
How to use lora models ?2:18
How to use lora models ? part24:41
How to use AnimateDiff pipeline?9:55
How to use AudioDML pipeline?3:19
How to use depthmap controlnet with your sd model ?9:05

How to install AUTOMATIC1111 on Windows ?8:01
How to add your stable diffusion models & control nets in AUTOMATIC1111 ?15:16
txt2img in AUTOMATIC111127:12
What are LoRA models ?30:26
How to train stable difusion models using LoRA method?6:32
img2img + inpainting + outpainting24:16
sketch + inpaint sketch18:17
How to create good prompt ?37:36
What is Regional Prompter ?14:10
Dynamic prompts12:48
open pose Controlnet7:55
How to upscale your image using controlnet ?4:42
How to use multi controlNets ?15:23
How to do perfect fingers ?14:14
How to use photopea editor in AUTOMATIC1111 ?19:27
control lighting with controlnet10:00
How to do zoom in and zoom out in automatic 1111 ?4:25
How can you convert your video into animation ??26:08

Requirements

Basic understanding of machine learning concepts
Programming skills

Description

Master Stable Diffusion, Generative AI, and AI Image & Video Generation from the ground up with one of the most comprehensive hands-on courses available. Whether you want to understand how diffusion models work internally or build real AI-powered applications with Python, this course will take you from the mathematical foundations to advanced real-world implementations.

Unlike courses that only demonstrate AI tools, this course explains the technology behind them. You will first understand the theory of diffusion models, including Gaussian Distribution, Markov Chains, Forward and Reverse Diffusion, DDPM, DDIM, U-Net architecture, Positional Embeddings, and the complete Stable Diffusion pipeline. Then, you will apply this knowledge by building and using modern AI image generation systems with Python.

Throughout the course, you will implement real projects using Stable Diffusion, ControlNet, DreamBooth, LoRA, Hugging Face Diffusers, AnimateDiff, and AUTOMATIC1111. You will learn how to generate high-quality AI images, perform image-to-image generation, inpainting, outpainting, style transfer, portrait animation, AI video generation, and fine-tune your own diffusion models.

This course combines deep theoretical explanations with practical coding sessions. Every major concept is accompanied by Python implementations so that you understand not only how to use these technologies but also why they work.

What you'll learn

Understand Diffusion Models from first principles
Build diffusion models with Python
Master Stable Diffusion architecture
Learn DDPM and DDIM algorithms
Train and fine-tune DreamBooth models
Fine-tune models using LoRA
Generate realistic AI images
Create AI videos and image animations
Master ControlNet for advanced image generation
Perform Inpainting and Outpainting
Work with Hugging Face Diffusers
Build Stable Diffusion applications with Python
Understand U-Net architecture and Positional Embeddings
Learn image-to-image generation techniques
Apply diffusion models to real-world AI projects

Who this course is for:

Python developers interested in Generative AI
Machine Learning and Deep Learning engineers
Computer Vision engineers
AI researchers and graduate students
Developers who want to understand Stable Diffusion beyond simply using existing tools
Anyone interested in building AI image and video generation applications

Master Stable Diffusion with Python: AI Images & Video

What you'll learn

Explore related topics

Course content

Introduction20 lectures • 2hr 8min

Unconditional diffusion model10 lectures • 3hr 42min

Stable diffusion model9 lectures • 2hr 10min

Video to AI Animation with stable diffusion from scratch15 lectures • 4hr 58min

EMO: Emote Portrait Alive6 lectures • 35min

Portrait Image Animation2 lectures • 10min

Recap For Diffusers Library10 lectures • 1hr 15min

AUTOMATIC111118 lectures • 4hr 57min

CNC and AI Art: Bringing Stable Diffusion Images to the Real World2 lectures • 20min

AI With Architecture 20253 lectures • 7min

Requirements

Description

Who this course is for: