currently i am working on a new workflow. until that time i find dreambooth + realistic vision
currently i am working on a new workflow. until that time i find dreambooth + realistic vision
Flooks like time to time we need to delete venv entirely
Fmy previous installation was adding noise to the generated images
Fnew installation didnt make
Fgenerated over 5k 768x1024 px class images
Falso tested different models for realism
Fand realistic vision is still the best realistic one
Fthere was a github repo which had real photos of real people
Fdo you remember its address
Fvery weird
F1 extension is causing defects in image
AWhich extension?
Fdont know yet
Fi have these
F
Fpreparing the best ever class images dataset
Fcant find a good model that can properly identify abnormal images :/
Fmaybe i should fetch real images from unsplash
Dif you get this, is the best thing to do wait or to transfer to another gpu instance
Nyes I want it to generate class images because I dont have any. DrFurkan said dev is working for him so maybe its just a matter of updating it for the template somehow?
ADepends whether you are able to wait or not, you can try waiting, otherwise transfer your data to another pod if you don't want to wait, because you have no idea how long you will have to wait for a GPU to become available.
Fi decided to collect real images
Fwritten script to download from unsplah
Fcan be used even for fine tuning
AJust pull the dev branch
FDownloading class images
FNok 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