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