Diffusion Mastery: Flux, Stable Diffusion, Midjourney & More

Diffusion Mastery: Flux, Stable Diffusion, Midjourney & More
Published 9/2024
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz

AI Images and Videos: Stable Diffusion, ComfyUI, Forge WebUI, Runway, MidJourney, DALL-E, Adobe Firefly, Flux, Leonardo

What you’ll learn

Introduction to Diffusion Models: Basics and first steps with diffusion models

Stable Diffusion & Flux: Using open-source models, negative prompts, LoRAs for SDXL or Flux

Guides for installing and using tools like Fooocus, ComfyUI, Forge, locally or in the cloud

Flux: Usage for inpainting, IP Adapter, ControlNets, custom LoRAs, and more

Training custom models & LoRAs, checkpoints, encoders, inpainting and upscaling, multiline prompts for creative image generation

Creative Applications: Creating consistent characters, AI influencers, product placements, changing clothes and styles (e.g., anime)

Specialized workflows and tools: Using tools like ComfyUI, Forge, Fooocus, integrating ControlNets, advanced prompting, and logo design

Deepfakes: Faceswapping in photos and videos, installing programs for live deepfakes in Python, voice cloning, and legal concerns

AI voices and music: Creating audiobooks, sound effects, and music with tools like Elevenlabs, Suno, Udio, and OpenAI API

AI videos: Producing AI films with Hotshot, Kling AI, Runway, Pika, Dreammachine, Deforum, WrapFusion, Heygen, and more

Upscaling and sound enhancement: Improving image, video, and sound quality, higher resolution, or converting to vector formats

Ethics and security: Legal frameworks and data protection in the use of diffusion models

Requirements

No prior knowledge or technical expertise required, everything will be shown step by step.

Description

Overview

Section 1: Introduction

Lecture 1 Welcome

Lecture 2 My Goal and a Few Tips

Lecture 3 Explanation of the Links

Lecture 4 Important Links

Section 2: How Diffusion Models Work: Examples & Your First Image with DALL-E

Lecture 5 What Will We Learn in This Section?

Lecture 6 Examples of Diffusion Models and Their Applications

Lecture 7 Diffusion Models in Detail: Embeddings, Tensors, RGB Codes & More

Lecture 8 Create a ChatGPT Account and Your First Image with DALL-E

Lecture 9 Recap: What You Should Do NOW

Section 3: Basics & Prompt Engineering for Diffusion Models: DALL-E as Example

Lecture 10 What Will Be Covered in This Section?

Lecture 11 Basics of Prompt Engineering for Diffusion Models (in DALL-E)

Lecture 12 How to Structure Prompts

Lecture 13 DALL-E Is Simple Because ChatGPT Helps

Lecture 14 Magic Words for Diffusion Models

Lecture 15 Optimizing Aspect Ratios for Different Platforms

Lecture 16 Using Reference Images in DALL-E

Lecture 17 Image Editing and Inpainting with DALL-E in ChatGPT

Lecture 18 Custom Instructions for Better Prompts

Lecture 19 My Custom Instructions

Lecture 20 Develop Your Own GPT to Optimize Prompts

Lecture 21 Training Data from My GPT & Link to GPT

Lecture 22 The Gen_ID in DALL-E Is Like the Seed: Create Consistent Characters

Lecture 23 Recap: What You Should Remember!

Section 4: Basics of Stable Diffusion: Negative Prompts, Models, LoRAs & First Images

Lecture 24 What Is This Section About?

Lecture 25 Stable Diffusion & Flux: Features of Open-Source Diffusion Models

Lecture 26 Using Stable Diffusion in Fooocus with Google Colab or locally

Lecture 27 Fooocus Basics: Interface, First Steps, Settings, and Images

Lecture 28 Stable Diffusion Prompting: Order, Negative Prompts, Brackets & Weighting

Lecture 29 Full Body Views with Aspect Ratio, Prompts & Negative Prompts

Lecture 31 More Prompt Engineering Tips for Stable Diffusion and find Styles

Lecture 32 Create SDXL Prompts with Your Own GPT

Lecture 33 Summary: Important Points to Remember

Section 5: Fooocus for Advanced Users: Inpainting, Input Image, Upscaling, LoRAs & More

Lecture 34 What Will We Learn in This Section?

Lecture 35 Multiline Prompts in Stable Diffusion: Blending Images Together

Lecture 36 Support for Arrays and Brackets in Multi-Prompting

Lecture 38 Enhancing Faces, Eyes, Hands, Clothes, and Details with Enhance

Lecture 39 Stable Diffusion Inpainting Basics

Lecture 40 Stable Diffusion Outpainting Basics

Lecture 41 Improving Hands with Inpainting & perspecitve field

Lecture 42 Input Image and Input Prompt

Lecture 43 Controlnet Pyra Canny: Pose to Image

Lecture 44 ControlNet Depth to Image: Implementing Poses and Depths with CPDS

Lecture 45 FaceSwap and Combining ControlNets

Lecture 46 Consistent Characters: Illustrating a Picture Book, for Example, with Animals

Lecture 47 Installing Checkpoints & LoRAs Locally

Lecture 48 Checkpoints & LoRAs in Google Colab: SDXL Turbo for FAST Generations

Lecture 49 Recap: What You Should Remember

Section 6: Stable Diffusion Pro: Consistent Characters, Product Placements, Clothing, etc.

Lecture 50 What Will We Learn in This Section?

Lecture 51 Creating Perfect Consistent Characters and Optimizing FaceSwap

Lecture 52 FaceSwap with Advanced Inpainting and Developer Debug Mode

Lecture 54 Consistent Characters with Grids for Special Poses & Stories

Lecture 55 Creating & Changing Clothing with Masks & Inpainting: AI can Market Cloths

Lecture 56 Real live Product Placements and Better Understanding Masks

Lecture 57 Perfect Hair with Inpainting, Image Prompt, and Masks

Lecture 58 Describe & Converting Photos to Anime Style and Vice Versa

Lecture 59 Using Metadata to Recreate Images

Lecture 60 Text in Stable Diffusion

Lecture 61 Summary: Important Points to Remember

Section 7: Train Your Own SDXL LoRa: On Your Face, on AI-Influencer or on Animals

Lecture 62 What Will We Learn in This Section? Training Stable Diffusion LoRAs!

Lecture 63 Creating a Dataset to train your SDXL model

Lecture 64 Quick Tipp on your Dataset for SDXL Dreambooth training

Lecture 65 Make a Huggingface token: API Key for Pushing Models to Huggingface

Lecture 66 Train your Stabe Diffusion XL LoRA with Dreambooth inside Google Colab

Lecture 67 Using SDXL Kohya LoRA in Fooocus

Lecture 68 Recap: What You Should Remember!

Section 8: Flux.1 Basics, different option and running it locally in WebUI Forge

Lecture 69 What Is This About? Flux in Forge!

Lecture 70 Information About Flux and Black Forest Labs

Lecture 71 Different Ways to Efficiently Use Flux.1 Pro, Dev, and Schnell

Lecture 72 Installing Forge WebUI: Using Stable Diffusion & Flux Easily

Lecture 73 Forge Interface: Using Stable Diffusion & LoRas in Forge WebUI

Lecture 74 Flux in of Forge: Find the Rigth Model (GGUF, NF4, FP16, FP8, Dev, Schnell)

Lecture 75 Prompt Engineering for Flux

Lecture 76 LoRas for Flux

Lecture 77 Upscaling with Forge WebUI

Lecture 78 Inpainting and img2img with Flux in Forge WebUI

Lecture 79 Important Points to Remember

Section 9: Basics in ComfyUI with Flux.1 and more

Lecture 80 What Is This Section About? ComfyUI Basics

Lecture 81 Installing ComfyUI: Using Flux and Stable Diffusion Locally

Lecture 82 Using SDXL Models in ComfyUI

Lecture 83 Prompt Engineering Info for ComfyUI, Flux & Stable Diffusion

Lecture 84 Using SDXL LoRAs, Creating ComfyUI Workflows and understand Metadata

Lecture 85 Installing the ComfyUI Manager from GitHub

Lecture 86 Using Flux Schnell and Dev Locally in ComfyUI

Lecture 87 Using Flux LoRAs in ComfyUI

Lecture 88 Using Flux for Low-End PCs: GGUF and Q2-Q8 Models

Lecture 89 Use my ComfyUI Workflows and find new ones

Lecture 90 ComfyUI Workflows

Lecture 91 Recap: What You Should Remember

Section 10: Train your own Flux LoRa

Lecture 92 What Is This Section About? Flux LoRa training for Logos & more

Lecture 93 Flux.1 dev: Train a LoRa Model on Replicate, FalAI or locally

Lecture 94 Use the Flux LoRa in Replicate for Inference

Lecture 95 Use Your LoRa Locally in ComfyUI or Forge WebUI

Lecture 96 Recap: What You Should Remember about Flux LoRa Training

Section 11: ComfyUI & Flux Expert: ControlNets, IP-Adapter, Upscaling, Videos & more

Lecture 97 What Will We Learn in This Section about ComfyUI

Lecture 98 Using ControlNet for Flux in ComfyUI: Canny, Depth and Hed

Lecture 99 SDXL Controlnets and Workflows for ComfyUI

Lecture 100 Flux IP Adapter: Consistent Character with just 1 Input Image

Lecture 101 Ip Adapter for Stable Diffusion and some thougths

Lecture 102 Upscaling Workflows in ComfyUI with Flux, SDXL & SUPIR

Lecture 103 LivePortrait in ComfyUI: Animate Facial expression

Lecture 104 Examples of ComfyUI Capabilities: Videos, FaceSwap, Deforum & more

Lecture 105 Important Points to Remember

Lecture 106 There Are Thousands of Ways to Use Stable Diffusion

Lecture 107 Leonardo AI: Using Stable Diffusion Easily and Fast with Controlnets & more

Lecture 109 Ideogram: Not really Stable Diffusion

Lecture 110 Important Points to Remember

Section 13: MidJourney Basics: A User-Friendly & Powerful Diffusion Model

Lecture 111 What Will You Learn in This Section about Midjourney?

Lecture 112 MidJourney Signup, Interface and Overview

Lecture 113 Prompt Engineering and Settings in MidJourney

Lecture 115 Image Editing with MidJourney: Inpaint & Outpaint in the Editor

Lecture 116 Prompt Generators for MidJourney

Lecture 117 What You Should Remember

Section 14: MidJourney for Advanced Users

Lecture 118 What Will We Learn in This Section?

Lecture 119 Consistent Characters & Images in Prompts (Cref, Sref, Image Prompt)

Lecture 120 Image Weights: Assign Different Weights to Images and Text

Lecture 121 Multiprompting and Prompt Weights in MidJourney

Lecture 122 The -no Command, Multiprompts & Weights (Negative Prompts?)

Lecture 123 Describe Function: MidJourney Helps with Your Prompts

Lecture 124 Tip: Tiling for Creating Repeating Patterns

Lecture 125 Creating Text in MidJourney

Lecture 126 Permutation Prompting and the Seed in MidJourney

Lecture 127 STOP, Repeat, Quality & Remaster: Hidden Tools in MidJourney

Lecture 128 Videos in MidJourney

Lecture 129 Important Summary for MidJourney: What You Should Remember!

Section 15: Adobe Firefly

Lecture 130 Adobe Firefly vs. DALL-E, MidJourney & Stable Diffusion

Lecture 131 Basics of Adobe Firefly

Section 16: AI Videos from Text, Videos, Images, and Individual Frames

Lecture 132 What Will Be Covered in This Section?

Lecture 133 AI Videos: The Overview – What’s Available & Creating Videos with FLUX

Lecture 134 Hotshot: Text to Video Made Simple and Fast

Lecture 135 Kling AI: Text-to-Video, Image-to-Video, Motion Brush & Viral Aging Videos

Lecture 136 DreamMachine from LumaLabs: Recreating Viral Videos

Lecture 137 RunwayML: Everything You Need to Know

Lecture 138 Pika Labs: From Standard to Video Editing and LipSync

Lecture 139 Heygen: AI Avatars, AI Clones, Voice Translations, and More

Lecture 140 Stable Diffusion Videos: Deforum and WrapFusion

Lecture 141 Stable WrapFusion in Google Colab

Lecture 142 Overview of Deforum Diffusion to make Ai-Animation

Lecture 143 Mkae AI Music Videos with Deforum Diffusion

Lecture 144 Create 3D Animation in Deforum Stable Diffusion

Lecture 145 Recap of AI Videos

Section 17: AI-Generated Voices, Music & DeepFakes

Lecture 146 Diffusion Models Can Generate Voices, Sounds & Music: An Overview

Lecture 147 ElevenLabs TTS: Everything You Need to Know (Audio, Sound, Voice Cloning & more)

Lecture 148 Open-Source Text-to-Speech Solution: ChatTTS

Lecture 149 Real-Time Deepfake with Webcam, Images & Videos Deep-Live-Cam Locally in Python

Lecture 150 Steps for Deepfake (Copy my Code Lines)

Section 18: Overview of Upscaling Images, Videos, Vectors & Audio Enhancement

Lecture 151 Upscaling Images, Videos, and Vectors

Lecture 152 Improving Audio Quality with Adobe Podcast

Section 19: Diffusion Safety: Copyright, NSFW Content, Privacy & More

Lecture 153 Copyright & Intellectual Property: Can You Sell Outputs & Create NSFW Content

Lecture 154 Privacy for Personal Content

Section 20: Impact of Diffusion on the Future, Society & Job Market

Lecture 155 The Future with Diffusion Models