e2462ba2dc
Change dataloader to correctly pair training and regularization images
2022-10-01 13:56:27 +10:00
648b87a200
Modifications to support multiple identifier training
2022-10-01 10:53:24 +10:00
5239367089
Turning off flip.
2022-09-28 16:18:09 -05:00
589f6ea5ed
changed 'demoura' to 'joepenna' for README.md
2022-09-26 18:06:04 -07:00
3d97f68047
ddpm changes
2022-09-25 22:23:08 -07:00
25e5c2520e
get rid of pycache stuff and make work with windows
2022-09-25 17:09:41 -07:00
650c887c69
Update attention.py
2022-09-25 16:26:55 -07:00
56ee2882fb
Merge branch 'main' of https://github.com/JoePenna/Dreambooth-Stable-Diffusion
2022-09-24 01:05:18 -07:00
5b9603f803
Merge branch 'XavierXiao:main' into main
2022-09-24 00:36:38 -07:00
2545d3565c
Pulling in Xavier's changes
2022-09-24 00:36:14 -07:00
ce7d1dffe7
Improvements by David Bielejeski, Niko Pueringer, Maki99
2022-09-24 00:32:50 -07:00
a22c61800d
Update util.py
2022-09-20 21:48:16 -07:00
99c2e27053
Tweaks for training people
...
A few tweaks to the repo to help training faces, though I've also used these same settings to train objects and styles.
Also adding a notebook to make it easier to run the code on vast.ai / runpod / other cloud computing platforms.
2022-09-17 16:00:31 -07:00
8f22429d74
initial commit
2022-09-06 00:00:21 -07:00
Kane Wallmann