Just pull the dev branch ``` cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
Just pull the dev branch
FDownloading class images
F
Nok let me try report back
NHello guys!
Got errors on Step 5: pip install -r requirements.txt
Got errors on Step 5: pip install -r requirements.txt
Fi wonder should i train a realistic model for humans :d
Fthat means requirements file is problematic
Fneed to be fixed
Fbefore installing you can try this
Fgit checkout 61c8f06c98055b8e0c3ced91ec35a23273bad694
Fthat is a working verison
Fmake a new venv
N@ashleyk I updated the dev branch and it even has a popup that says fixed class images. But I tried it again, same error @Dr. Furkan Gözükara any ideas?
Fwill let you know once i do a training
Fpreparing class images
L(venv) C:\deepface\roop>python run.py --gpu
Traceback (most recent call last):
File "C:\deepface\roop\run.py", line 3, in <module>
from roop import core
File "C:\deepface\roop\roop\core.py", line 15, in <module>
from opennsfw2 import predict_video_frames, predict_image
ModuleNotFoundError: No module named 'opennsfw2' I am getting this error :/ someone know ?
Traceback (most recent call last):
File "C:\deepface\roop\run.py", line 3, in <module>
from roop import core
File "C:\deepface\roop\roop\core.py", line 15, in <module>
from opennsfw2 import predict_video_frames, predict_image
ModuleNotFoundError: No module named 'opennsfw2' I am getting this error :/ someone know ?
AHmmm looks like its still broken, I will test it in a bit
Fc++ tools missing
LI'm a newbie sorry, but I already installed it? I think I forgot a step
Loh fine, i got it thx
Flet me know results
L(venv) C:\deepface\roop>python run.py --keep-frames --keep-fps --gpu
Traceback (most recent call last):
File "C:\deepface\roop\run.py", line 3, in <module>
from roop import core
File "C:\deepface\roop\roop\core.py", line 23, in <module>
import roop.globals
File "C:\deepface\roop\roop\globals.py", line 1, in <module>
import onnxruntime
ModuleNotFoundError: No module named 'onnxruntime'
Traceback (most recent call last):
File "C:\deepface\roop\run.py", line 3, in <module>
from roop import core
File "C:\deepface\roop\roop\core.py", line 23, in <module>
import roop.globals
File "C:\deepface\roop\roop\globals.py", line 1, in <module>
import onnxruntime
ModuleNotFoundError: No module named 'onnxruntime'
HHow to continue training from a checkpoint in shivamshrirao repo with Colab?
A@Dr. Furkan Gözükara have you used Tensorboard to monitor learning rate, loss etc?
NIt worked! Thx)
Famazing auto cropping the pictures
F
F
Fpreparing the best every fine tuning / classification dataset
Fthis is easy
Fyou are skipping steps
FGitHub
Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks - Stable-Diffusion/1-Click-DeepFake-Tutorial.md at main · FurkanGozukara/Stable-Diffusion
FYouTubeSECourses
Our Discord : https://discord.gg/HbqgGaZVmr. This is the video where you will learn how to use Google Colab for Stable Diffusion. 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 Stable Diffusion Tutorials, #Automatic1111...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, #Automatic1111...
Fgreat
Fi think they are not very useful for stable diffusion
AHow do I fix this issue:
AThe pod has a GPU so I don't understand why its doing this.
AAWill it still function correctly if I add
--skip-torch-cuda-testIt doesn't like the
Works fine on
NVIDIA GeForce RTX 3090Works fine on
NVIDIA RTX A5000
Ehey quick question. im not familiar with fp16 vs bf16. I am setting up Kohya right now. what difference between fp16 vs bf16? (i have rtx 3070 GPU)
Fyour gpu supports both
Fyou can pick either
Eokay thanks! one of these options would increase training speed?
Fi would chose bf16
Fman been working whole day
Ffull real pictures classification dataset
Fcoming to the patreon
AYeah, I don't understand it either, because I am pretty sure you said you were using that GPU type in RunPod 
AThis is awesome, will it working better than the usual classification images?
