I used this command instead and it worked: pip install xformers==0.0.17.dev464 Is it ok ?
I used this command instead and it worked:
pip install xformers==0.0.17.dev464
Is it ok ?
pip install xformers==0.0.17.dev464
Is it ok ?
Bgotcha. also, one more thing. so I have the deleted the pod on which i trained yesterday. but now I want to fine tune the model even more. the steps will be the same?
Fyou need to upload same model
Fto continue training 
For it will beging from 0
Boh yes that i'll upload, do i select this model as the base model in dreamboot and then create another new dreambooth model?
Fyep that is the idea
Bcool.
Bcan i use 2GPUs that'll give me 48gb vram and 83gb ram in total or i have to use one 1 gpu
FYou can't combine vram of them atm
FBut you can run 2 instance of web ui
Bok
VLaunch errors detected: ['Incorrect version of torch installed.', 'Incorrect version of torchvision installed.']
VI followed exactly your commands 
TTest 3 of todays dreambooth config used from the video except learning rate. I change from .000002 to .000006 to .000001 and change my epoch from 200 to 180, 15 image. Daam Sd its like spending my whole life 
V[!] torch version 1.13.1+cu116 installed.
[!] torchvision version 0.14.1+cu116 installed.
[+] accelerate version 0.16.0 installed.
[+] bitsandbytes version 0.35.4 installed.
[+] diffusers version 0.13.1 installed.
[+] transformers version 4.26.1 installed.
[+] xformers version 0.0.17.dev464 installed.
Launch errors detected: ['Incorrect version of torch installed.', 'Incorrect version of torchvision installed.']
[!] torchvision version 0.14.1+cu116 installed.
[+] accelerate version 0.16.0 installed.
[+] bitsandbytes version 0.35.4 installed.
[+] diffusers version 0.13.1 installed.
[+] transformers version 4.26.1 installed.
[+] xformers version 0.0.17.dev464 installed.
Launch errors detected: ['Incorrect version of torch installed.', 'Incorrect version of torchvision installed.']
VWould you plz tell me what's I'm doing wrong ?
Fok do this
Fpip uninstall torchvision
Fpip uninstall torch
Frestart web ui
VSo no need to install torch ?
VSo I think after restarting the system installed by itself. and here is the result . But when I go to dreambooth all buttons are disabled
V
Bclick on create tab
VNow it's ok 
B
Fye now looks good
Frecorded a new video to just show
Fhow to install on runpod lol :d
AT_T why does my multi-controlnet isn't working?
Fmust be misisng some step
Fdont forget git pull
AI can't use use it properly for some reasons
I can only use it for only 1 controlnet per generation.
If I tried to use 2 controlnet in the same time only the first, controlnet will be applied
I can only use it for only 1 controlnet per generation.
If I tried to use 2 controlnet in the same time only the first, controlnet will be applied
Sdreambooth extention cant make lora files. you need to extract, and lora extraction is always crappy
AI can only use 1 controlnet sir.
AIf I tried to use more than 1, only the first will work.
Sits avesome it worked out for you now
Fit should work
Fthey are working on it
AYeah technically it should sir
Fit will be able to make lore useable like kohya
Abut something was wrong about it in my PC
AI can't use both depth and openpose models for perfect pose+hand T_T
Sabout time
Ahere are the proofs
Fyes
