Go to file
Victor Hall be2cec7d3b
Update Train_Colab.ipynb
2024-02-23 11:33:09 -05:00
.devcontainer Split requirements between build and runtime 2023-04-01 00:29:10 +02:00
.github update docker tags 2023-11-16 12:04:39 -05:00
cfgs update coco example cfg 2023-02-25 16:37:10 -05:00
data fix oopsie 2023-12-22 13:54:20 -05:00
doc add cog-vlm to citations 2024-02-03 14:52:16 -05:00
docker Misc minor fixes 2023-11-09 00:22:41 +01:00
examples flamingo 2023-06-29 18:12:52 -04:00
optimizer Using -1.0 instead of -1. 2023-11-17 21:55:12 +02:00
plugins fix issue with plugin interaction with validation 2023-12-22 13:52:26 -05:00
scripts add tokenizer tester script 2023-11-25 17:21:34 -05:00
test Fix undersize warning 2023-10-05 01:48:09 -03:00
utils fix reshaping for picking apps 2023-11-29 22:17:52 -05:00
.gitignore Add docker compose file 2023-05-28 12:42:57 -07:00
.pylintrc gitignore 2022-12-17 22:34:07 -05:00
CaptionFL.ipynb set highmem and t4 for colab 2023-07-03 15:37:29 -04:00
LICENSE update license for 2023 2023-01-27 13:59:02 -05:00
LICENSE_AGPL update license for 2023 2023-01-27 13:59:02 -05:00
README.md add some citations and references links 2023-11-17 12:56:53 -05:00
Train_Colab.ipynb Update Train_Colab.ipynb 2024-02-23 11:33:09 -05:00
Train_JupyterLab.ipynb jupyter notebook fix to upload ldm safetensors instead of ckpt 2023-11-18 13:33:22 -05:00
activate_venv.bat hey look ed2 2022-12-17 22:32:48 -05:00
activate_venv.ps1 add ps activate script 2023-12-21 14:02:36 -05:00
caption.py BLIP2 was loading into system RAM rather than VRAM for me. I found that adding argument "device_map=device" forces it to load the entire model onto the specified device. I tested it for cuda and cpu successfully. 2024-01-06 15:16:59 -05:00
caption_cog.py Cough... fixed typo 2024-02-06 18:11:20 +09:00
caption_fl.py fix caption fl 2023-07-03 15:58:30 -04:00
caption_kosmos2.py remove errant print from kosmos script 2023-11-03 13:50:49 -04:00
chain.bat update ed1 mode 2023-01-09 13:44:51 -05:00
chain0.json chaining and more lowers resolutions 2023-01-08 18:52:39 -05:00
chain1.json chaining and more lowers resolutions 2023-01-08 18:52:39 -05:00
chain2.json chaining and more lowers resolutions 2023-01-08 18:52:39 -05:00
docker-compose.yml Add docker compose file 2023-05-28 12:42:57 -07:00
optimizer.json update windows to torch 2.1 and add attention type option 2023-11-24 16:13:01 -05:00
optimizerSD21.json updating reqs 2023-11-02 21:54:33 -04:00
optimizer_dadapt.json Update optimizer_dadapt.json 2023-08-04 22:13:52 -04:00
requirements-test.txt test reqs 2023-05-08 18:25:37 -04:00
requirements.txt removing open flamingo from requirements.txt 2023-11-26 12:33:04 -05:00
sample_prompts.json Update sample_prompts.json 2023-02-27 19:57:08 -06:00
sample_prompts.txt hey look ed2 2022-12-17 22:32:48 -05:00
train.json update windows to torch 2.1 and add attention type option 2023-11-24 16:13:01 -05:00
train.py prevent OOM with disabled unet when gradient checkpointing is enabled 2024-01-16 10:23:52 +13:00
trainSD21.json update ema sample args again 2023-09-18 16:12:51 -04:00
validation_default.json update docs for every_n_epochs 2023-05-07 12:05:49 +02:00
windows_setup.cmd removing open flamingo from standard installs and documenting, OF is broken in torch2.1 unfortunately 2023-11-26 12:51:58 -05:00

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!

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.

Patreon or Kofi.

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

Setup and installation

Download and setup base models

Data Preparation

Training - How to start training

Troubleshooting

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

Shuffling Tags

Data Balancing - Includes my small treatise on model "preservation" with additional ground truth data

Logging

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

Contributing

Citations and references