you should be careful? maybe it can be a legal problem to you?
you should be careful? maybe it can be a legal problem to you?
Fi dont know
Fi can change link to somewhere else
Fmaybe i will put into a fake hugging face repo haha
Fdo you know any code repository that supports over 100 mb file?
Fi'd use wetransfer or something like that
Fthere are some anonymous
Fyou uploaded it to your personal HF account XDD
FGPU support added : https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/1-Click-DeepFake-Tutorial.md
GitHub
Best Stable Diffusion and AI Tutorials, Guides, News, Tips and Tricks - Stable-Diffusion/1-Click-DeepFake-Tutorial.md at main · FurkanGozukara/Stable-Diffusion
Fwhat is the change for linux?
Fcudnn?
Fdont know linux :/
Fyou can download from nvidia i guess
Fi mean if the difference is cudnn
Fthey fixed with in code
Fso now works
Fwith also 1 extra dll
Foh so it's another commit
Fgit checkout e4f1d9aaff43549667f7c81c6f48a86606fb9b95Fthis one or you forgot to change it?
Fno need
Flatest working
Fok!
FIf you get error and can't fix it (repo keep getting new updates) do these then reinstall
Fmoved it to very bottom
Fgoing to the gym afk
AD:\deepfake\roop>python run.py --keep-frames --keep-fps --max-cores 1
Traceback (most recent call last):
File "D:\deepfake\roop\run.py", line 15, in <module>
from opennsfw2 import predict_image as face_check
ModuleNotFoundError: No module named 'opennsfw2' i am getting this error
Traceback (most recent call last):
File "D:\deepfake\roop\run.py", line 15, in <module>
from opennsfw2 import predict_image as face_check
ModuleNotFoundError: No module named 'opennsfw2' i am getting this error
FInstall c++ tools. Restart. Do a new clone and reinstall
CI noticed that I can run "python launch.py", but this doesn't provide a public url, I tried passing "--share", but this doesn't work
ATry adding
--listen too.
Cstill doesn't work
Frunpod?
Cyes sir
Fyou have to edit template overrides and add the port
ANormal port for runpod is 3000 not 7861, so add
--port 3000 too. You don't actually need to use the share option with runpod, it can assign a public IP and map port 3000 to a port on your public IP, which you can obtain by looking at the "Connect" option from the RunPod web interface.F3000 is automatic111
F7861 is kohya
Fand you can't change the port on kohya as far as i know
F--port is not a valid option
Fbut anyway --share fixes it for sure
AOh I see, wasn't aware it was Kohya_ss
ANew RunPod template version with Jupyter fixed:
https://runpod.io/gsc?template=67x2of4db7&ref=w18gds2n
RunPod environment variables for overriding template defaults is currently broken, so you can't set
https://runpod.io/gsc?template=67x2of4db7&ref=w18gds2n
RunPod environment variables for overriding template defaults is currently broken, so you can't set
JUPYTER_PASSWORD, the default password is rn51hunbpgtltcpac3olCedited the template and it appears to expose that port 7861 but doesn't run on launch. I run command "python launch.py --nowebui" and it still provides a local url
CI added --share but does the same thing
AI am pretty sure you want a webui with Khoya_ss, there is no reason to disable that unless you are using Stable Diffusion WebUI and only interested in making API calls and not using the actual Web UI itself.
Cyeah, that's what i'm interested in, just making api calls
Ci'm following the instructions in https://towardsdatascience.com/stable-diffusion-as-an-api-5e381aec1f6 but struggling with the networking aspect
ACan't read this article, it wants me to pay. Are you using Khoya_ss? I am not aware of it having an API.
Cyou must have hit your limit. i'm using whatever is in the "RunPod Stable Diffusion v1.5+v2" template on runpod
Ci'm new to this space and don't really know what khoya_ss is
AThats not Khoya_ss @felixsanz , unless you installed it afterwards, but the template does not include it by default, it includes the Automatic1111 Web UI by default.