Mirrors
/
EveryDream
mirror of https://github.com/victorchall/EveryDream.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update README.MD 

Signed-off-by: Victor Hall <victor.charles.hall@gmail.com>
This commit is contained in:
Victor Hall 2023-01-05 01:32:23 -05:00 committed by GitHub
parent e711d08165
commit f844156e32
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.MD
View File

@ -2,6 +2,8 @@
This repo will contain tools for data engineering efforts for people interested in taking their fine tuning beyond the initial DreamBooth paper implementations for Stable Diffusion, and may be useful for other image projects. This repo will contain tools for data engineering efforts for people interested in taking their fine tuning beyond the initial DreamBooth paper implementations for Stable Diffusion, and may be useful for other image projects.
If you are looking for trainers, check out [EveryDream 1.0](https://github.com/victorchall/EveryDream-trainer) and [EveryDream 2](https://github.com/victorchall/EveryDream2trainer). This is just a toolkit repo for data work but works in concert with those trainers.
For instance with Stable Diffusion, by using ground truth Laion data mixed in with training data to replace "regularization" images, together with clip-interrogated captioning or original TEXT caption from laion, or human-geneated labels, training quality can be improved. These are a significant steps towards towards full fine tuning capabilities. For instance with Stable Diffusion, by using ground truth Laion data mixed in with training data to replace "regularization" images, together with clip-interrogated captioning or original TEXT caption from laion, or human-geneated labels, training quality can be improved. These are a significant steps towards towards full fine tuning capabilities.
Captioned training together with regularization has enabled multi-subject and multi-style training at the same time, and can scale to larger training efforts. Captioned training together with regularization has enabled multi-subject and multi-style training at the same time, and can scale to larger training efforts.