Completed
Introduction to #StableDiffusion #TextualInversion Embeddings
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
How to Do Stable Diffusion Textual Inversion - Text Embeddings by Automatic1111 Web UI Tutorial
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction to #StableDiffusion #TextualInversion Embeddings
- 2 Which commit of the #Automatic1111 Web UI we are using and how to checkout / switch to specific commit of any Git project
- 3 Used command line arguments of Automatic1111 webui-user.bat file
- 4 Automatic1111 command line arguments
- 5 How to and where to put Stable Diffusion models and VAE files in Automatic1111 installation
- 6 Why do we use latest VAE file and what does VAE file do
- 7 Training settings of Automatic1111
- 8 All about names of text embeddings
- 9 What is initialization text of textual inversion training
- 10 Embedding inspector extension of Automatic1111
- 11 How to set number of vectors per token when doing Textual Inversion training
- 12 Technical and detailed explanation of tokens and their numerical weights vectors in Stable Diffusion
- 13 How the prompts getting tokenized - turned into tokens - by using tokenizer extension
- 14 Setting number of training vectors
- 15 Where embedding files are saved in automatic1111 installation
- 16 All about preprocess images before TI training
- 17 Training tab of textual inversion
- 18 What to and how to set embedding learning rate
- 19 What are the Batch size and Gradient accumulation steps and how to set them
- 20 How to set training learning rate according to Batch size and Gradient accumulation steps
- 21 What are prompt templates, what are they used for, how to set and use them in textual inversion training
- 22 What are filewords and how they are used in training in automatic1111 web ui
- 23 How to edit image captions when doing textual inversion training
- 24 From training images pool, how and why did i choose some of them and not all of them
- 25 Why I did add noise to the backgrounds of some training dataset images
- 26 How should be your training dataset. What is a good training dataset
- 27 Save TI training checkpoints
- 28 Which latent sampling method is best
- 29 Training started
- 30 Overclock GPU to get 10% training speed up
- 31 Where to find TI training preview images
- 32 Where to see used final prompts during training
- 33 How to use inspect_embedding_training script to determine overtraining of textual inversion
- 34 What is training loss
- 35 Technical difference of Textual Inversion, DreamBooth, LoRA and HyperNetworks training
- 36 Over 200 epochs and already got very good sample preview images
- 37 How to set newest VAE file as default in the settings of automatic1111 web ui
- 38 How to use generated embeddings checkpoint files
- 39 How to test different checkpoints via X/Y plot and embedding files name generator script
- 40 How to upscale image by using AI
- 41 How to use multiple embeddings in a prompt