EveryDream2trainer/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!](.github/discord_sm.png)](https://discord.gg/nQaxwrPT)

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](.github/patreon-medium-button.png)](https://www.patreon.com/everydream) or  [![Kofi](.github/kofibutton_sm.png)](https://ko-fi.com/everydream).

If you're coming from Dreambooth, please [read this](doc/NOTDREAMBOOTH.md) 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](#cloud) section below.

## Video tutorials

### [Basic setup and getting started](https://www.youtube.com/watch?v=OgpJK8SUW3c) 

Covers install, setup of base models, startning training, basic tweaking, and looking at your logs

### [Multiaspect and crop jitter explainer](https://www.youtube.com/watch?v=0xswM8QYFD0)


Behind the scenes look at how the trainer handles multiaspect and crop jitter

## Cloud/Docker

### [Free tier Google Colab notebook](https://colab.research.google.com/github/victorchall/EveryDream2trainer/blob/main/Train_Colab.ipynb)

### * [RunPod / Vast Instructions](/doc/CLOUD_SETUP.md)
#### * [Vast.ai Video Tutorial](https://www.youtube.com/watch?v=PKQesb4om9I)
#### [Runpod Video Tutorial](https://www.youtube.com/watch?v=XAULP-4hsnA)

### [Docker image link](https://github.com/victorchall/EveryDream2trainer/pkgs/container/everydream2trainer)

## Docs

[Setup and installation](doc/SETUP.md)

[Download and setup base models](doc/BASEMODELS.md) 

[Data Preparation](doc/DATA.md)

[Training](doc/TRAINING.md) - How to start training

[Troubleshooting](doc/TROUBLESHOOTING.md)

[Basic Tweaking](doc/TWEAKING.md) - Important args to understand to get started

[Advanced Tweaking](doc/ADVANCED_TWEAKING.md) and [Advanced Optimizer Tweaking](/doc/OPTIMIZER.md)

[Chaining training sessions](doc/CHAINING.md) - Modify training parameters by chaining training sessions together end to end

[Shuffling Tags](doc/SHUFFLING_TAGS.md)

[Data Balancing](doc/BALANCING.md) - Includes my small treatise on model "preservation" with additional ground truth data

[Logging](doc/LOGGING.md) 

[Validation](doc/VALIDATION.md) - Use a validation split on your data to see when you are overfitting and tune hyperparameters

[Captioning](doc/CAPTION.md) - tools to generate synthetic captioning (recommend [Cog](doc/CAPTION_COG.md))

[Plugins](doc/PLUGINS.md) - (beta) write your own plugins to execute arbitrary code during training

[Contributing](doc/CONTRIBUTING.md)

[Citations and references](doc/CITATIONS.md)
hey look ed2 2022-12-17 20:32:48 -07:00			`# EveryDream Trainer 2.0`

remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 20:24:03 -06:00			`Welcome to v2.0 of EveryDream trainer! Now with more Diffusers, faster, and even more features!`
fixes 2022-12-17 22:43:25 -07:00
update docs 2023-03-18 22:59:17 -06:00			`For the most up to date news and community discussions, please join us on Discord!`
hey look ed2 2022-12-17 20:32:48 -07:00
Update README.md fix discord inv link 2024-06-14 15:20:46 -06:00			`[![Discord!](.github/discord_sm.png)](https://discord.gg/nQaxwrPT)`
update docs 2023-03-18 22:59:17 -06:00
			`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](.github/patreon-medium-button.png)](https://www.patreon.com/everydream) or [![Kofi](.github/kofibutton_sm.png)](https://ko-fi.com/everydream).`
hey look ed2 2022-12-17 20:32:48 -07:00
doc, fix lr defaulting bug, notdreambooth.md, read multicaption from .txt by line 2023-02-26 17:11:42 -07:00			`If you're coming from Dreambooth, please [read this](doc/NOTDREAMBOOTH.md) for an explanation of why EveryDream is not Dreambooth.`

sys req on main readme 2023-02-28 08:57:49 -07:00			`## Requirements`

			`Windows 10/11, Linux (Ubuntu 20.04+ recommended), or use the linux Docker container`
Update README.md 2023-03-08 21:47:33 -07:00
sys req on main readme 2023-02-28 08:57:49 -07:00			`Python 3.10.x`
Update README.md 2023-03-08 21:47:33 -07:00
sys req on main readme 2023-02-28 08:57:49 -07:00			`Nvidia GPU with 11GB VRAM or more (note: 1080 Ti and 2080 Ti may require compiling xformers yourself)`
Update README.md 2023-03-08 21:47:33 -07:00
sys req on main readme 2023-02-28 08:57:49 -07:00			`16GB system RAM recommended minimum`

			`Single GPU is currently supported`
Update README.md 2023-03-08 21:47:33 -07:00
sys req on main readme 2023-02-28 08:57:49 -07:00			`32GB of system RAM recommended for 50k+ training images, but may get away with sufficient swap file and 16GB`
Update README.md 2023-03-08 21:47:33 -07:00
update docs 2023-03-18 22:59:17 -06:00			`Ampere or newer 24GB+ (3090/A5000/4090, etc) recommended for 10k+ images`
sys req on main readme 2023-02-28 08:57:49 -07:00
update docs 2023-03-18 22:59:17 -06:00			`...Or use any computer with a web browser and run on Vast/Colab. See [Cloud](#cloud) section below.`
sys req on main readme 2023-02-28 08:57:49 -07:00
minor update 2022-12-18 15:21:13 -07:00			`## Video tutorials`

			`### [Basic setup and getting started](https://www.youtube.com/watch?v=OgpJK8SUW3c)`

			`Covers install, setup of base models, startning training, basic tweaking, and looking at your logs`
add vast-runpod video links to main readme 2023-04-15 12:25:39 -06:00
			`### [Multiaspect and crop jitter explainer](https://www.youtube.com/watch?v=0xswM8QYFD0)`

minor update 2022-12-18 15:21:13 -07:00
			`Behind the scenes look at how the trainer handles multiaspect and crop jitter`

add vast-runpod video links to main readme 2023-04-15 12:25:39 -06:00			`## Cloud/Docker`

			`### [Free tier Google Colab notebook](https://colab.research.google.com/github/victorchall/EveryDream2trainer/blob/main/Train_Colab.ipynb)`

			`### * [RunPod / Vast Instructions](/doc/CLOUD_SETUP.md)`
			`#### * [Vast.ai Video Tutorial](https://www.youtube.com/watch?v=PKQesb4om9I)`
			`#### [Runpod Video Tutorial](https://www.youtube.com/watch?v=XAULP-4hsnA)`

			`### [Docker image link](https://github.com/victorchall/EveryDream2trainer/pkgs/container/everydream2trainer)`

hey look ed2 2022-12-17 20:32:48 -07:00			`## Docs`

			`[Setup and installation](doc/SETUP.md)`

minor update 2022-12-18 15:21:13 -07:00			`[Download and setup base models](doc/BASEMODELS.md)`
hey look ed2 2022-12-17 20:32:48 -07:00
			`[Data Preparation](doc/DATA.md)`

more docs, more docs, more docs, ok stop docs 2023-01-23 14:28:23 -07:00			`[Training](doc/TRAINING.md) - How to start training`
hey look ed2 2022-12-17 20:32:48 -07:00
remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 20:24:03 -06:00			`[Troubleshooting](doc/TROUBLESHOOTING.md)`
fixes 2022-12-17 22:43:25 -07:00
remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 20:24:03 -06:00			`[Basic Tweaking](doc/TWEAKING.md) - Important args to understand to get started`
chaining and more lowers resolutions 2023-01-08 16:52:39 -07:00
Update README.md 2023-04-14 01:12:44 -06:00			`[Advanced Tweaking](doc/ADVANCED_TWEAKING.md) and [Advanced Optimizer Tweaking](/doc/OPTIMIZER.md)`
optimizer doc 2023-02-25 14:19:23 -07:00
more docs, more docs, more docs, ok stop docs 2023-01-23 14:28:23 -07:00			`[Chaining training sessions](doc/CHAINING.md) - Modify training parameters by chaining training sessions together end to end`
Implemented an optimization for the shuffling if all tags have the same weight and added documentation. 2023-01-07 14:59:51 -07:00
			`[Shuffling Tags](doc/SHUFFLING_TAGS.md)`
more docs, more docs, more docs, ok stop docs 2023-01-23 14:28:23 -07:00
remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 20:24:03 -06:00			`[Data Balancing](doc/BALANCING.md) - Includes my small treatise on model "preservation" with additional ground truth data`

			`[Logging](doc/LOGGING.md)`
doc and bug with undersized 2023-02-06 11:11:24 -07:00
validation docs 2023-02-08 14:11:09 -07:00			`[Validation](doc/VALIDATION.md) - Use a validation split on your data to see when you are overfitting and tune hyperparameters`

add huber loss, timestep clamping, slightly safer txt reading 2024-04-26 21:54:31 -06:00			`[Captioning](doc/CAPTION.md) - tools to generate synthetic captioning (recommend [Cog](doc/CAPTION_COG.md))`
document flamingo caption script 2023-06-29 22:28:07 -06:00
add plugin doc link 2023-07-04 15:36:57 -06:00			`[Plugins](doc/PLUGINS.md) - (beta) write your own plugins to execute arbitrary code during training`

remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 20:24:03 -06:00			`[Contributing](doc/CONTRIBUTING.md)`
readme updates 2023-02-18 12:49:30 -07:00
add some citations and references links 2023-11-17 10:56:53 -07:00			`[Citations and references](doc/CITATIONS.md)`