The End of Photography - Use AI to Make Your Own Studio Photos Via DreamBooth Training

Learn how to create studio-quality photos using AI with this comprehensive tutorial on DreamBooth training for Stable Diffusion. Install and use the DreamBooth extension for Automatic1111 Web UI, explore realism workflows, and master techniques for generating high-quality images. Discover how to prepare training datasets, configure settings for optimal results, and utilize classification images effectively. Gain insights into checkpoint comparison, image sorting, and quality improvement through inpainting and ControlNet. Perfect for those interested in leveraging AI for professional-grade photography without the need for traditional studio setups.

Dreambooth training with Automatic1111 Web UI
How to install DreamBooth extension of Automatic1111 Web UI
Automatic installer script for DreamBooth extension
Manual installation of DreamBooth extension
How to use older / certain version of Auto1111 or DreamBooth with git checkout
Main manual installation part of DreamBooth extension
How to manually update previously installed DreamBooth extension to the latest version
How to install requirements of DreamBooth extension
How to use DreamBooth extension
How to compose your training model in DreamBooth extension
Best base model and settings for realism training in DreamBooth
Where to find installed Python ,xFormers, Torch, Auto1111 versions
How to solve frozen / non-progressing CMD window
Where the DreamBooth generated training files native diffusers are stored
Where the Stable Diffusion training files are stored
Select training model and start setting parameters for best realism
How to continue training later a time
Which configuration settings tab for best realism and best training
Concept tab settings
How to prepare your training images dataset with my human cropping script and pre-processing
What kind of training images you should have for DreamBooth training
Continue back setting parameters for concepts tab
Everything about classification / regularization images used during Dreambooth / LoRA training
Used pre-prepared real images based classification images for this tutorial
How to generate classification images by using the trained model
How to generate images with Automatic1111 forever until cancelled
How to use image captions with DreamBooth extension via [filewords]
How to automatically generate captions for training or class images
How to use BLIP or deepbooru for captioning
What happens when image caption is read, what is the final output of instance prompt
How to set class images per instance
What is the benefit of using real photos as classification images
How to start training after setting all configuration
Training started, displayed messages on CMD
When it generates new classification images
What if if you don't have such powerful GPU for such quality training
How to do x/y/z checkpoint comparison to find best checkpoint
How checkpoints are named when saved - 1 epoch step count
The best VAE file I use for best quality
How to open x/y/z plot comparison results and evaluate them
How sort thousands of generated image with the best similarity thus quality
How to improve generated image quality via 2 different inpainting methodology
Improve results with inpainting + ControlNet
What is important to get good quality images after inpainting