817f4169ce
GIT was failing because its processor returns a BatchEncoding and its method to() only accepts one device parameter, so I removed the second dtype parameter and it worked. I don't see how BLIP2 is different, but it works with both parameters, so I left it to avoid breaking any functionality. |
||
|---|---|---|
| .devcontainer | ||
| .github | ||
| cfgs | ||
| data | ||
| doc | ||
| docker | ||
| examples | ||
| optimizer | ||
| plugins | ||
| scripts | ||
| test | ||
| utils | ||
| .gitignore | ||
| .pylintrc | ||
| CaptionFL.ipynb | ||
| LICENSE | ||
| LICENSE_AGPL | ||
| README.md | ||
| Train_Colab.ipynb | ||
| Train_JupyterLab.ipynb | ||
| activate_venv.bat | ||
| activate_venv.ps1 | ||
| caption.py | ||
| caption_fl.py | ||
| caption_kosmos2.py | ||
| chain.bat | ||
| chain0.json | ||
| chain1.json | ||
| chain2.json | ||
| docker-compose.yml | ||
| optimizer.json | ||
| optimizerSD21.json | ||
| optimizer_dadapt.json | ||
| requirements-test.txt | ||
| requirements.txt | ||
| sample_prompts.json | ||
| sample_prompts.txt | ||
| train.json | ||
| train.py | ||
| trainSD21.json | ||
| validation_default.json | ||
| windows_setup.cmd | ||
README.md
EveryDream Trainer 2.0
Welcome to v2.0 of EveryDream trainer! Now with more Diffusers, faster, and even more features!
For the most up to date news and community discussions, please join us on Discord!
If you find this tool useful, please consider subscribing to the project on Patreon or a one-time donation on Ko-fi. Your donations keep this project alive as a free open source tool with ongoing enhancements.
or 
.
If you're coming from Dreambooth, please read this for an explanation of why EveryDream is not Dreambooth.
Requirements
Windows 10/11, Linux (Ubuntu 20.04+ recommended), or use the linux Docker container
Python 3.10.x
Nvidia GPU with 11GB VRAM or more (note: 1080 Ti and 2080 Ti may require compiling xformers yourself)
16GB system RAM recommended minimum
Single GPU is currently supported
32GB of system RAM recommended for 50k+ training images, but may get away with sufficient swap file and 16GB
Ampere or newer 24GB+ (3090/A5000/4090, etc) recommended for 10k+ images
...Or use any computer with a web browser and run on Vast/Colab. See Cloud section below.
Video tutorials
Basic setup and getting started
Covers install, setup of base models, startning training, basic tweaking, and looking at your logs
Multiaspect and crop jitter explainer
Behind the scenes look at how the trainer handles multiaspect and crop jitter
Companion tools repo
Make sure to check out the tools repo, it has a grab bag of scripts to help with your data curation prior to training. It has automatic bulk BLIP captioning for BLIP, script to web scrape based on Laion data files, script to rename generic pronouns to proper names or append artist tags to your captions, etc.
Cloud/Docker
Free tier Google Colab notebook
* RunPod / Vast Instructions
* Vast.ai Video Tutorial
Runpod Video Tutorial
Docker image link
Docs
Download and setup base models
Training - How to start training
Basic Tweaking - Important args to understand to get started
Advanced Tweaking and Advanced Optimizer Tweaking
Chaining training sessions - Modify training parameters by chaining training sessions together end to end
Data Balancing - Includes my small treatise on model "preservation" with additional ground truth data
Validation - Use a validation split on your data to see when you are overfitting and tune hyperparameters
Captioning - (beta) tools to automate captioning
Plugins - (beta) write your own plugins to execute arbitrary code during training