Stable Diffusion DreamBooth Tutorial Using Automatic1111 Web UI - Ultra Detailed
Software Engineering Courses - SE Courses via YouTube
Overview
Syllabus
Introduction to Grand Master yet most beginner friendly Stable Diffusion Dreambooth tutorial by using Automatic1111 Web UI
How to install DreamBooth extension to the Web UI
How to update installed extensions on the Web UI
Introduction to DreamBooth extension tab
Training model generation for DreamBooth
How to download official SD model files
Training model selection and settings tab of the DreamBooth extension
What is training steps per image epochs
Checkpoint saving frequency
What is training batch size in DreamBooth training and how to set them properly
Set gradients to none when zeroing
Gradient checkpoint
Image processing and resolution
Horizontal flip and Center crop
What is Sanity sample prompt and how to utilize it to understand overtraining
Best options to set in Advanced tab of DreamBooth extension
Step Ratio of Text Encoder Training
Concepts tab of the DreamBooth extension
How to crop images from any position with Paint .NET or use Birme .NET
Setting training dataset directory
What are classification images
What is Instance prompt
How to and why to pick your instance prompt as a very rare word very crucial
Class of the subject
Everything about class prompt
Sample prompt
Clas images per instance
Number of samples to generate
Teach multiple concepts in 1 run
Saving tab
How to generate checkpoints during training
Generating class images before start training
What is batch size in txt2img tab
Start training
First samples/previews of training
Sanity prompt sample
How to understand overtraining with sanity samples
How to properly prepare your training dataset images
Checkpoint saving during training
What is Lr displayed in cmd during training
How to continue / resume training if an error occurs or you cancel it
We started to overtraining and how we understood it
How to start generating our subject face images from best trained checkpoint
What is prompt strength / attention / emphasis and how to increase it
How to increase image quality with negative prompts
How to get your taught subject with which correct prompting
What is CFG and why should we increase it
How to try multiple CFG scale values by using X/Y prompting
Analyzing CFG effect
How to test different artist styles with different CFG scales by using X/Y plot
How to use prompt matrix
Prompts from file or text box to test many different prompts
Generate thousands of images while sleeping
PNG info to learn used prompts, CFG, seed and others
Extras tab to upscale images by using AI models with awesome quality
How improve eyes and face quality by using GFPGAN
How to continue training from any saved ckpt checkpoint
How to upload your trained model to Google Colab to use
How to teach a new subject to your already trained model
How to use filewords for training
What is fine tuning and how it is done
Hybrid training
How to understand out of memory error
Lowest GPU VRAM settings
How to batch preprocess images
How to generate very correct descriptions by using GIT large model
How to inject your trained subject into any custom / new model
Where is model hash written and how to compare
Taught by
Software Engineering Courses - SE Courses