Completed
How to prepare your training images dataset with my human cropping script and pre-processing
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
The End of Photography - Use AI to Make Your Own Studio Photos Via DreamBooth Training
Automatically move to the next video in the Classroom when playback concludes
- 1 Dreambooth training with Automatic1111 Web UI
- 2 How to install DreamBooth extension of Automatic1111 Web UI
- 3 Automatic installer script for DreamBooth extension
- 4 Manual installation of DreamBooth extension
- 5 How to use older / certain version of Auto1111 or DreamBooth with git checkout
- 6 Main manual installation part of DreamBooth extension
- 7 How to manually update previously installed DreamBooth extension to the latest version
- 8 How to install requirements of DreamBooth extension
- 9 How to use DreamBooth extension
- 10 How to compose your training model in DreamBooth extension
- 11 Best base model and settings for realism training in DreamBooth
- 12 Where to find installed Python ,xFormers, Torch, Auto1111 versions
- 13 How to solve frozen / non-progressing CMD window
- 14 Where the DreamBooth generated training files native diffusers are stored
- 15 Where the Stable Diffusion training files are stored
- 16 Select training model and start setting parameters for best realism
- 17 How to continue training later a time
- 18 Which configuration settings tab for best realism and best training
- 19 Concept tab settings
- 20 How to prepare your training images dataset with my human cropping script and pre-processing
- 21 What kind of training images you should have for DreamBooth training
- 22 Continue back setting parameters for concepts tab
- 23 Everything about classification / regularization images used during Dreambooth / LoRA training
- 24 Used pre-prepared real images based classification images for this tutorial
- 25 How to generate classification images by using the trained model
- 26 How to generate images with Automatic1111 forever until cancelled
- 27 How to use image captions with DreamBooth extension via [filewords]
- 28 How to automatically generate captions for training or class images
- 29 How to use BLIP or deepbooru for captioning
- 30 What happens when image caption is read, what is the final output of instance prompt
- 31 How to set class images per instance
- 32 What is the benefit of using real photos as classification images
- 33 How to start training after setting all configuration
- 34 Training started, displayed messages on CMD
- 35 When it generates new classification images
- 36 What if if you don't have such powerful GPU for such quality training
- 37 How to do x/y/z checkpoint comparison to find best checkpoint
- 38 How checkpoints are named when saved - 1 epoch step count
- 39 The best VAE file I use for best quality
- 40 How to open x/y/z plot comparison results and evaluate them
- 41 How sort thousands of generated image with the best similarity thus quality
- 42 How to improve generated image quality via 2 different inpainting methodology
- 43 Improve results with inpainting + ControlNet
- 44 What is important to get good quality images after inpainting
