@Dr. Furkan Gözükara have you managed to get Drembooth to work locally with DeepSpeed? If so, have y
@Dr. Furkan Gözükara have you managed to get Drembooth to work locally with DeepSpeed? If so, have you had good results with that?
JHi, again an error of path right ?
HHello, very new to SD. I have installed Dreambooth extension in web UI using auto installer scripts on Runpod. I am trying to create what's shown in Corridor Digital crew video.
Any help to use Dreambooth like they did in using 4 datasets to train a model?
Any help to use Dreambooth like they did in using 4 datasets to train a model?
- Dataset1: Niko - The main subject (a real man's images for training data set)
- Dataset2: Ghibli Animation characters - images to train the main subject on
- Dataset3: General images of man (reg images)
- Dataset4: General images of art style (reg images)
B@FiveSAI sorry if I missed it, but did you already share your training parameters for sdxl dreambooth? 
interested in trying them out
interested in trying them out
Fi got up to date tutorials and install scripts
Fwhat you need
Fyes it can do
Fyou need to modify 1 file though
FGitHub
I had to modify this code to generate TensorRT that will support highres fix for SDXL self.max_image_shape = 768 if version in ("1.4", "1.5") else 2048 It is by default 1024 So ...
Fself.max_image_shape = 768 if version in ("1.4", "1.5") else 2048
F,i am using Kohya. waiting Triton package to be available on Windows
Falmost there
Fdoesnt show error
Fshow full error
Fhello welcome
Fi have 2 tutorials that shows their approach
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of #StableDiffusion Tutorials, Au...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusion Tutorials, Au...
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Turn your real video into an animation with just 1 click by using Stable Diffusion for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Sta...
https://www.patreon.com/SECoursesPlaylist of Sta...
Phumm have you ever run Koyah in WSL2?
Fnope
PToday I'm going to try to install it according to your video, I'm going to try in wsl2.
PI managed to make the latest version of the A1111 dreambooth work in wsl2 but it seems that this koyah must be better.
P*Kohya
Hwow thanks for sharing!
Sthanks i solve it i think XD i can run A1111 whit normaly! thanks you very much!
P@Dr. Furkan Gözükara Do you know if there is any known issue with Torch 2.1.0? I always see the dependencies pointing to 2.0.1. I did a test with 2.1.0 on my dreambooth 2.1.0 and noticed that it performed faster.
Malso interested in this topic since I tried an update from torch 2.0.1 to 2.1.1 with xformers 0.23 and couldn't get it to work. Always trying to figure out which dependencies are needed.
Pin A1111 i have this setup
Pwhat changes in xformers 0.23?
Mdidn't research changes - just that it was a newly released version and @Dr. Furkan Gözükara recently tested it in latest patreon
PWell, I'm going to test Kohya with its default configuration, after I get good results I'll do the experiment and try to update the dependencies to the most recent ones.
EDr, you think we can train this new realistic SDXL model (https://civitai.com/models/152525) with your config files as base? the model contains VAE baked inside already
Introducing Version 2.0 of the Realism Engine We are excited to announce that Version 2.0 of the Realism Engine is now available, featuring signifi...
P@Dr. Furkan Gözükara when you say that not using xformers with 24gb is better than using xformers with 16gb, does it mean that it only changes the quality of image rendering or affects the quality of training the face correctly?
TTo use Kandinsky, I had to downgrade my Transformers
PI don't know Kandisky but if it's some dependency restriction I might not be able to update it
TPytorch 2.1.1 is bad, use 2.1.0+cu118, as cu123 also bad
TI think better off using Kandinsky @fusionbrain
P
FI shared sdxl lora ones earlier, still testing all the possible settings, i got about 22 trainings left then will share my best one
Fi think depends on each project
Fbut on automatic1111 working so far
Fi replied you from patreon too
Fdon't forget to activate venv of Automatic1111 Web UI
pip uninstall torch torchvision torchaudio xformers --yes
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install xformers==0.0.23
pip uninstall torch torchvision torchaudio xformers --yes
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install xformers==0.0.23
Mthanks got it working with torch 2.1.1 and xformers 0.23
Fy4es you can
Fi should compare
Fgreat
Pwhen i started training
P
Pi received this warning
PtensorRT are used to train in kohya?