so the person should not get memorized but the cloth should be
so the person should not get memorized but the cloth should be
Fadd it to the requirements so it will get installed
Fah let me check
Fwhat is available 1 sec
Fxformers==0.0.17.dev476
Fthis is the strategy to get most recent one @AlaBeat
Fok what you need to do is simple
Fadd this to the requirements of dreambooth extension first
Fxformers==0.0.17.dev476
Fthen
Factivate venv and
Fexecute this command
Fpip install -r "path_of_SD_Extension\requirements.txt"
PYes it is, the generated persons are not important. Important is person must be wearing that clothing.
Fso you need to make model learn cloth but not the person
POK,I will try it,thank you
FThanks, you mean in here?
Fdoing some experiment for style video
Fyou can also add there
Fit should install
Fafter restart
Fsd extension is this one
Faccelerate==0.17.1
albumentations~=1.3.0
bitsandbytes==0.35.4
dadaptation==1.5.0
diffusers~=0.14.0
discord-webhook~=1.1.0
fastapi~=0.90.1
ftfy~=6.1.1
gitpython~=3.1.31
lion-pytorch~=0.0.7
mediapipe-silicon; sys_platform == 'darwin'
mediapipe; sys_platform != 'darwin'
modelcards~=0.1.6
tensorboard~=2.11.2
tensorflow==2.11.0; sys_platform != 'darwin' or platform_machine != 'arm64'
tensorflow-macos==2.11.0; sys_platform == 'darwin' and platform_machine == 'arm64'
tqdm~=4.64.1
transformers~=4.27.1
albumentations~=1.3.0
bitsandbytes==0.35.4
dadaptation==1.5.0
diffusers~=0.14.0
discord-webhook~=1.1.0
fastapi~=0.90.1
ftfy~=6.1.1
gitpython~=3.1.31
lion-pytorch~=0.0.7
mediapipe-silicon; sys_platform == 'darwin'
mediapipe; sys_platform != 'darwin'
modelcards~=0.1.6
tensorboard~=2.11.2
tensorflow==2.11.0; sys_platform != 'darwin' or platform_machine != 'arm64'
tensorflow-macos==2.11.0; sys_platform == 'darwin' and platform_machine == 'arm64'
tqdm~=4.64.1
transformers~=4.27.1
Fyou can also manually install
Factivate venv
Fand execute this command
Fpip install xformers==0.0.17.dev476
Fyou mean deleting the venv file like in the tuorial?
Fif you did it once you dont have to do again
Nrip
Fye looks like your card also not supporting torch 2
FI know spanish, let me know if you need help
Fi added a spanish subtitle to the video can you check how good it is
FYouTubeSECourses - Software Engineering Courses
Discord : https://bit.ly/SECoursesDiscord. Torch 2 / Pytorch 2 is now supported along with new DreamBooth Automatic1111 Web UI extension. 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
In this video, I am explaining how you can man...
https://www.patreon.com/SECoursesIn this video, I am explaining how you can man...
Fyou need to downgrade
Fgive me a minute
FTo downgrade back to older Torch first delete venv, let it reinstall, then activate venv and run this command pip install -r "path_of_SD_Extension\requirements.txt"
Fadd this to requirements file of dreambooth : xformers==0.0.17.dev476
Fit's perfect
Fawesome
FWhat model do you suggest using for training a face? the 1.5 base model? I expected to be able to use models like realistic vision or RPG but i never get a complete resemblance
Fusing 1.5 base model for training and then merging checkpoint with other can be better?
Aok so i got xformers==0.0.17.dev476 installed, but my loras still don't work it says that same error Additional Network extension not installed, Only hijack built-in lora
LoCon Extension hijack built-in lora successfully, not lora not locon working....
LoCon Extension hijack built-in lora successfully, not lora not locon working....
Ai've done a git pull command in the additional network extension folder, it said it updated some files, but still same error
Anow i'm doing the -r requirements.txt for the sd webui folder maybe that will change something
Aok tested 2 loras they work, but i still have Additional Network extension not installed, Only hijack built-in lora
LoCon Extension hijack built-in lora successfully thing error
LoCon Extension hijack built-in lora successfully thing error
Fbase 1.5 best
Fmerge can work
Aok tested 6 or more loras they all work, don't know what is causing that error or what it means
Finteresting