Tutorial series for how to use Stable Diffusion both on Google Colab and on your PC with Web UI interface - Install, Run, DreamBooth, Train, Models

Here the list of videos to with the order to follow

All videos are very beginner friendly - not skipping any parts and covering pretty much everything

Playlist link on YouTube:?Stable Diffusion - Dreambooth - txt2img - img2img - Embedding - Hypernetwork - AI Image Upscale

1.)

Easiest Way to Install & Run Stable Diffusion Web UI on PC by Using Open Source Automatic Installer

2.)

How to use Stable Diffusion V2.1 and Different Models in the Web UI - SD 1.5 vs 2.1 vs Anything V3

3.)

Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automatic1111 Web UI - Ultra Detailed

4.)

How To Do Stable Diffusion LORA Training By Using Web UI On Different Models - Tested SD 1.5, SD 2.1

5.)

How to Inject Your Trained Subject e.g. Your Face Into Any Custom Stable Diffusion Model By Web UI

6.)

How to Run and Convert Stable Diffusion Diffusers (.bin Weights) & Dreambooth Models to CKPT File

7.) If you don't have a strong GPU to do training then you can follow this tutorial to train on a Google Colab notebook, generate ckpt from trained weights, download it and use it on Automatic1111 Web UI

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusion - Better than Lensa for Free

8.)

How to Use SD 2.1 & Custom Models on Google Colab for Training with Dreambooth & Image Generation

The topics covered in these videos are as follows:

Easiest Way to Install & Run Stable Diffusion Web UI on PC by Using Open Source Automatic Installer

• 0:00 Intro - we are going to show 2 ways to install web UI on the PC
• 0:28 Developer of the Automatic Installer of the Stable Diffusion Web UI
• 0:31 Explanation of why we can trust this installer
• 0:58 From where how to download this automatic installer
• 1:26 How to start installation of the automatic installer. Run as administrator is the key
• 2:08 Installer exe beginning screen and we start to install
• 2:28 How you can find our Discord link to join and ask any questions
• 3:25 Where you can find more information related to different Stable Diffusion models and vae files
• 3:50 Pick the Web UI installation folder and start installation
• 5:29 How to send shortcut of installed launcher to the desktop and start the Stable Diffusion Web UI application
• 6:06 The launcher interface and settings
• 7:23 Which another video you must watch to understand how to use Stable Diffusion Web UI better
• 9:16 Web interface is started and we are doing first image generation
• 10:46 Entering prompt to start image generation
• 11:10 How to upscale an image by using AI - awesome quality
• 12:04 Starting manual installation of the Stable Diffusion Web UI from its GitHub folder
• 14:48 If you get error during Python installation, another version of this product already installed
• 15:55 How to verify installed and actively selected Python version
• 16:19 How to change default Python from environment variables path variable?
• 17:58 How to run Web UI from manually installed folder after installing Python
• 18:44 Fixing the encountered error during running the Web UI
• 20:15 How to install downloaded stable diffusion models
• 21:17 How to open started Web UI application

How to use Stable Diffusion V2.1 and Different Models in the Web UI - SD 1.5 vs 2.1 vs Anything V3

• 0:00 Introduction to the video
• 0:38 Official page of Stability AI who released Stable Diffusion models
• 1:14 How to download official Stable Diffusion version 2.1 with 768x768 pixels
• 1:44 How to copy paste the downloaded version 2.1 model into the correct web UI folder
• 2:05 Where to download necessary .yaml files which are the configuration file of Stable Diffusion models
• 2:41 Where to and how to save .yaml file in our web UI installation?
• 3:53 Modification of command parameters in webui-user.bat file to properly run version 2.1
• 4:55 What are command line arguments and where to find their full list
• 5:28 The importance of messages displayed in the command window of web ui app
• 6:05 Where to switch between models in the Stable Diffusion web-ui
• 6:36 Test results of version SD (Stable Diffusion) 1.5 with generic keywords
• 7:18 The important thing that you need to be careful when testing and using models
• 8:09 Test results of version SD (Stable Diffusion) 2.1 with generic keywords
• 9:20 How to load and use Analog Diffusion and its test results with generic keywords
• 9:57 Where to get yaml file for version 1.x based models and how to use it for version 1.x based models
• 10:36 Test results of version Stable Diffusion Anything V3
• 11:28 Where you can find different Stable Diffusion models?
• 12:17 Ending speech of the video

Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automatic1111 Web UI - Ultra Detailed

• 0:00 Introduction to Grand Master yet most beginner friendly Stable Diffusion Dreambooth tutorial by using Automatic1111 Web UI
• 3:11 How to install DreamBooth extension to the Web UI
• 4:09 How to update installed extensions on the Web UI
• 4:35 Introduction to DreamBooth extension tab
• 4:45 Training model generation for DreamBooth?
• 5:34 How to download official SD model files
• 6:21 Training model selection and settings tab of the DreamBooth extension
• 7:36 What is training steps per image epochs
• 8:24 Checkpoint saving frequency
• 9:15 What is training batch size in DreamBooth training and how to set them properly
• 10:47 Set gradients to none when zeroing
• 11:24 Gradient checkpoint
• 12:04 Image processing and resolution
• 12:39 Horizontal flip and Center crop
• 12:50 What is Sanity sample prompt and how to utilize it to understand overtraining
• 13:30 Best options to set in Advanced tab of DreamBooth extension
• 14:22 Step Ratio of Text Encoder Training
• 14:49 Concepts tab of the DreamBooth extension?
• 15:27 How to crop images from any position with Paint .NET or use Birme .NET
• 17:22 Setting training dataset directory
• 17:44 What are classification images
• 18:46 What is Instance prompt
• 19:05 How to and why to pick your instance prompt as a very rare word (very crucial)
• 21:52 Class of the subject
• 22:15 Everything about class prompt
• 22:55 Sample prompt
• 23:30 Clas images per instance
• 25:00 Number of samples to generate
• 26:27 Teach multiple concepts in 1 run
• 28:24 Saving tab
• 29:10 How to generate checkpoints during training
• 30:52 Generating class images before start training
• 33:28 What is batch size in txt2img tab
• 36:09 Start training
• 38:25 First samples/previews of training
• 39:13 Sanity prompt sample
• 39:54 How to understand overtraining with sanity samples
• 40:34 How to properly prepare your training dataset images
• 43:15 Checkpoint saving during training
• 44:30 What is Lr displayed in cmd during training
• 45:38 How to continue / resume training if an error occurs or you cancel it
• 46:41 We started to overtraining and how we understood it
• 48:24 How to start generating our subject (face) images from best trained checkpoint
• 50:09 What is prompt strength / attention / emphasis and how to increase it?
• 51:17 How to increase image quality with negative prompts?
• 51:50 How to get your taught subject with which correct prompting
• 52:31 What is CFG and why should we increase it
• 52:54 How to try multiple CFG scale values by using X/Y prompting?
• 54:54 Analyzing CFG effect
• 56:03 How to test different artist styles with different CFG scales by using X/Y plot
• 1:00:47 How to use prompt matrix
• 1:02:54 Prompts from file or text box to test many different prompts?
• 1:03:57 Generate thousands of images while sleeping
• 1:04:22 PNG info to learn used prompts, CFG, seed and others
• 1:07:00 Extras tab to upscale images by using AI models with awesome quality
• 1:09:54 How improve eyes and face quality by using GFPGAN
• 1:11:35 How to continue training from any saved ckpt checkpoint
• 1:12:06 How to upload your trained model to Google Colab and generate images there
• 1:14:19 How to teach a new subject to your already trained model
• 1:15:55 How to use filewords for training
• 1:21:52 What is fine tuning and how it is done
• 1:23:10 Hybrid training
• 1:24:39 How to understand out of memory error
• 1:25:39 Lowest GPU VRAM settings
• 1:27:35 How to batch preprocess images
• 1:31:47 How to generate very correct descriptions by using GIT large model
• 1:33:19 How to inject your trained subject into any custom / new model
• 1:37:36 Where is model hash written and how to compare

How To Do Stable Diffusion LORA Training By Using Web UI On Different Models - Tested SD 1.5, SD 2.1

• 0:00 Introduction speech
• 1:07 How to install the LoRA extension to the Stable Diffusion Web UI
• 2:36 Preparation of training set images by properly sized cropping
• 2:54 How to crop images using Paint .NET, an open-source image editing software
• 5:02 What is Low-Rank Adaptation (LoRA)
• 5:35 Starting preparation for training using the DreamBooth tab - LoRA
• 6:50 Explanation of all training parameters, settings, and options
• 8:27 How many training steps equal one epoch
• 9:09 Save checkpoints frequency
• 9:48 Save a preview of training images after certain steps or epochs
• 10:04 What is batch size in training settings
• 11:56 Where to set LoRA training in SD Web UI
• 13:45 Explanation of Concepts tab in training section of SD Web UI
• 14:00 How to set the path for training images
• 14:28 Classification Dataset Directory
• 15:22 Training prompt - how to set what to teach the model
• 15:55 What is Class and Sample Image Prompt in SD training
• 17:57 What is Image Generation settings and why we need classification image generation in SD training
• 19:40 Starting the training process
• 21:03 How and why to tune your Class Prompt (generating generic training images)
• 22:39 Why we generate regularization generic images by class prompt
• 23:27 Recap of the setting up process for training parameters, options, and settings
• 29:23 How much GPU, CPU, and RAM the class regularization image generation uses
• 29:57 Training process starts after class image generation has been completed
• 30:04 Displaying the generated class regularization images folder for SD 2.1
• 30:31 The speed of the training process - how many seconds per iteration on an RTX 3060 GPU
• 31:19 Where LoRA training checkpoints (weights) are saved
• 32:36 Where training preview images are saved and our first training preview image
• 33:10 When we will decide to stop training
• 34:09 How to resume training after training has crashed or you close it down
• 36:49 Lifetime vs. session training steps
• 37:54 After 30 epochs, resembling images start to appear in the preview folder
• 38:19 The command line printed messages are incorrect in some cases
• 39:05 Training step speed, a certain number of seconds per iteration (IT)
• 39:25 Results after 5600 steps (350 epochs) - it was sufficient for SD 2.1
• 39:44 How I'm picking a checkpoint to generate a full model .ckpt file
• 40:23 How to generate a full model .ckpt file from a LoRA checkpoint .pt file
• 41:17 Generated/saved file name is incorrect, but it is generated from the correct selected .pt file
• 42:01 Doing inference (generating new images) using the text2img tab with our newly trained and generated model
• 42:47 The results of SD 2.1 Version 768 pixel model after training with the LoRA method and teaching a human face
• 44:38 Setting up the training parameters/options for SD version 1.5 this time
• 48:35 Re-generating class regularization images since SD 1.5 uses 512 pixel resolution
• 49:11 Displaying the generated class regularization images folder for SD 1.5
• 50:16 Training of Stable Diffusion 1.5 using the LoRA methodology and teaching a face has been completed and the results are displayed
• 51:09 The inference (text2img) results with SD 1.5 training
• 51:19 You have to do more inference with LoRA since it has less precision than DreamBooth
• 51:39 How to give more attention/emphasis to certain keywords in the SD Web UI
• 52:51 How to generate more than 100 images using the script section of the Web UI
• 54:46 How to check PNG info to see used prompts and settings
• 55:24 How to upscale using AI models
• 56:12 Fixing face image quality, especially eyes, with GFPGAN visibility
• 56:32 How to batch post-process
• 57:00 Where batch-generated images are saved
• 57:18 Conclusion and ending speech

How to Inject Your Trained Subject e.g. Your Face Into Any Custom Stable Diffusion Model By Web UI

• 0:00 Introduction to how to inject / merge / combine your models by using checkpoint merger
• 1:48 Start of the tutorial
• 1:57 My face trained model used training dataset
• 2:12 The image quality of the default trained model (SD 1.5 official version)
• 2:44 How to inject your trained info from your trained model into a new custom model
• 3:04 What are primary model, secondary model and tertiary model?
• 3:32 What is the strategy for extracting your trained subject from trained model and inject into a new custom model?
• 4:31 What is Checkpoint Merger multiplier
• 5:01 Add Difference selection
• 5:25 How to use newly merged model
• 5:54 How to select proper prompt strength and CFG value for the new subject injected model
• 9:22 How to join our discord channel to ask anything and get support for free

How to Run and Convert Stable Diffusion Diffusers (.bin Weights) & Dreambooth Models to CKPT File

• 0:00 How to run Stable Diffusion Diffuser (.bin / weight) models
• 0:41 How to install Visual Studio Community edition and Python
• 1:26 How to compose a Visual Studio Python project
• 2:40 How to install necessary libraries in a Visual Studio Python project such as CUDA enabled/compiled PyTorch, Torch, Diffusers, Transformers
• 5:43 How to install Accelerate in a Visual Studio Python project
• 6:04 How to run / start Hugging Face Diffusers or any type Hugging Face Python project inside a Visual Studio Python project
• 9:12 How to convert Stable Diffusion Diffuser project / model into a ckpt file
• 10:00 How to download / clone entire repository of a Hugging Face model while preserving its structure and file names by using Git Bash
• 11:29 How to download and use convert_diffusers_to_original_stable_diffusion.py script to generate ckpt file
• 14:04 How to load generated ckpt file into the Automatic1111 web UI application?
• 15:31 How to fix size mismatch for model.diffusion_model.input_blocks error happened on the new generated ckpt file
• 16:13 We generated our first artworks of lambdalabs/dreambooth-avatar
• 16:29 How to teach your own face to lambdalabs/dreambooth-avatar model by DreamBooth to generate your avatar portrait artwork
• 17:59 How to join our Discord channel to get help and support us on Patreon

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusion - Better than Lensa for Free

• 0:00 Introduction and the content
• 2:04 How to check you have enough Google drive space
• 2:18 Starting to prepare Google Colab notebook for Stablediffusion Dreambooth model training
• 5:01 Register, login and generate Hugging Face token for training of the AI model
• 6:56 Continue training setup of the Stable Diffusion Dreambooth
• 7:41 Setting the settings of Stable Diffusion Dreambooth model
• 9:08 Providing our own photos to train the model to teach our own face image
• 11:58 How to install Paint NET for image cropping
• 12:12 How to crop and prepare your training images by using Paint NET
• 13:36 How bulk image crop online with birme net website
• 14:50 How to quickly check all images dimensions in a folder by using sort options (width, height) in detailed folder view
• 15:26 How to upload training images to Google Colab
• 17:53 Starting training with last settings / options
• 18:11 Optimal parameters for training of Stable Diffusion Dreambooth model AI
• 22:42 Training of the AI model done
• 25:55 Exiting application/notebook completely and starting again to show how to use trained model
• 28:00 Starting to generate AI / Lensa app magic avatars
• 30:20 First avatar is generated and displayed
• 31:14 Explanation of the positive / inference prompt input to generate avatar images
• 32:44 Explanation of the negative prompt input to avoid such images, guidance_scale & num_inference_steps parameter of Stable Diffusion
• 36:47 New avatars with different guidance_scale parameter
• 37:34 How to generate colored portrait avatars / profile images
• 38:57 Showcasing different styles of generated avatars
• 40:00 Debated usage of artist styles
• 40:26 Continue to generate more artworks
• 42:18 Prompt for asian style artworks like korean, or japan or anime
• 44:45 Long hair, different eye color version of me
• 46:43 Adding armor keyword
• 47:22 Further tuning of input prompt
• 51:21 Cherry picking the results
• 54:27 How to generate hundreds or thousands of magic avatars as a batch
• 55:59 Clip of ~200 Stable Diffusion AI generated avatars
• 57:40 Ending talk and discussion

How to Use SD 2.1 & Custom Models on Google Colab for Training with Dreambooth & Image Generation

• 0:00 How to use different custom models in the Google Colab notebook
• 1:06 How to fix revision parameter to make custom models work in Stable Diffusion Google Colab Dreambooth notebook
• 2:16 How to use Stable Diffusion 2.1 on the Google Colab Dreambooth notebook
• 2:58 How to change vae files to get better quality results with Stable Diffusion
• 3:24 How to do inference (image generation) with Stable Diffusion 2.1 on the Google Colab Dreambooth notebook
• 4:03 Necessary code changes to run Version 2.1 on the Stable Diffusion Google Colab Dreambooth notebook
• 4:40 Generating 768x768 pixels images with SD 2.1 on the Google Colab notebook
• 5:09 How to return back SD 1.5 version on the Stable Diffusion Google Colab Dreambooth notebook
• 6:05 You don't have to do training to do inference (generating images)
• 6:19 You can do training on different custom models as well
• 6:30 When I say version 1.5 I refer to all models that are trained from 1.x Stable Diffusion models?
• 7:04 The code changes between different prime version numbers 1.x vs 2.x
• 7:27 Ending speech of the tutorial guide