Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
188 Commits 6 Branches 0 Tags 5.4 MiB
Python 87%
Jupyter Notebook 11.9%
Dockerfile 0.7%
Batchfile 0.2%
Shell 0.2%
Go to file
Joel Holdbrooks 326d861a86 Push DLMA into main, pass config to resolve 
This patch

* passes the configuration (`argparse.Namespace`) to the resolver,
* pushes the DLMA code into the main function,
* makes DLMA take a `list[ImageTrainItem]` instead of `data_root`,
* makes `EveryDreamBatch` take `DLMA` instead of `data_root`, etc.
* allows `data_root` to be a list.

By doing these things, both `EveryDreamBatch` and DLMA can be free from
data resolution logic. It also reduces the number of arguments which
need to be passed down to EDB and DLMA.
 		2023-01-29 17:08:54 -08:00
.github funding 2022-12-17 22:35:43 -05:00
data Push DLMA into main, pass config to resolve 2023-01-29 17:08:54 -08:00
doc change training example to constant lr 2023-01-28 18:20:04 -05:00
scripts early iter on txt2img script for testing on remote instances 2023-01-23 16:51:00 -05:00
test Push DLMA into main, pass config to resolve 2023-01-29 17:08:54 -08:00
utils fix colab notebook 2023-01-25 20:55:24 -05:00
.gitignore Remove empty line 2023-01-26 12:17:09 +01:00
.pylintrc gitignore 2022-12-17 22:34:07 -05:00
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 more docs, more docs, more docs, ok stop docs 2023-01-23 16:28:23 -05:00
Train_Colab.ipynb Update Train_Colab.ipynb 2023-01-27 01:08:46 -06:00
Train_Runpod.ipynb Simplify example training 2023-01-24 01:12:56 +01:00
activate_venv.bat hey look ed2 2022-12-17 22:32:48 -05:00
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
sample_prompts.txt hey look ed2 2022-12-17 22:32:48 -05:00
train.json update train.json example 2023-01-17 19:42:07 -05:00
train.py change training example to constant lr 2023-01-28 18:20:04 -05:00
trainSD21.json sd21 example json config 2023-01-26 12:07:28 -05:00
windows_setup.cmd ctrl-alt-pgup to generate sample 2023-01-12 00:40:49 -05:00

README.md

EveryDream Trainer 2.0

Welcome to v2.0 of EveryDream trainer! Now with more diffusers and even more features!

Companion tools

Please join us on Discord! https://discord.gg/uheqxU6sXN

If you find this tool useful, please consider subscribing to the project on Patreon or a one-time donation at Ko-fi.

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

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

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.

Docs

Setup and installation

Download and setup base models

Data Preparation

Training - How to start training

Basic Tweaking - Important args to understand to get started

Logging

Advanced Tweaking - More stuff to tweak once you are comfortable

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 ground truth data