Home
Artists
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register
Partychan Telegram Find&Fuck Waifus ThePornDude
Home Artists Posts Import Register

Some info on the next SD update (Patreon)

Published:
2022-11-30 17:41:01
Imported:
2023-01

Content

Got Dreambooth to work with the new 2.0 model.

Right now there is quite a few types of models for SD.

Regular, 2.0, inpainting, Upscale, Depth2Img.

I'm redoing some of the code so is easier to handle all those types + future models.

I'm also taking a look on my TODO list to add some of suggestions in there. There was big updates after big updates (dreambooth, 2.0 models) so its been some time I was able to add some stuff from the TODO list.

Edit: Also, I probably will start using MEGA to upload the files, to help everyone.

Comments

Anonymous

It would be very helpful if there was a FAQ or a step-by-step procedure for installing each version as it is released. I started with version 0.41 and upgraded to new releases 0.51 and 0.52. Those versions installed and ran great. I installed 0.56 and it ran great. When I downloaded 0.58 it seems to install with no obvious errors after extracting the rar file. But when I open version 0.58, the console window opens, gives the normal torchvision error and then starts to print to the console window some other errors. But then the console window closes abruptly and the GUI Window never opens. The window closes so fast, I can't read the errors it is showing. I assume I need to configure some new things for version 0.58. But I don't know how to do that. Any help will be appreciated.

cool1
>>96975366

If you copied the Lite version of 0.58 then it says you need to "copy the models and torch folder from the older build," and also that upscaling won't work in that lite version. So you'd go into the stable diffusion GRisk GUI 0.56 folder and copy the models and torch folders from there and paste them into the GRisk GUI 0.58 folder (if you go the lite version that didn't have those folders).

Anonymous

Exception: Loss is NaN, stopping training Been running into this. Thoughts? Additionally, my folder is all 512x512 PNGs.

DAINAPP
>>97042899

NaN is if your weights explode. Very common on model training. Use smaller Learning Rate.