A6000 training sdxl kohya - 48gb config file, around 8000 steps, 3 hours makes sense?
A6000 training sdxl kohya - 48gb config file, around 8000 steps, 3 hours makes sense?
Fgood idea
Fi see there dreambooth and lora tabs
F
Fyou need special notebook we shared on patreon
Fyou really are not following what i am telling you
Fadd --medvram
Fassuming it is 12 gb vram
Fyes you can use. but dreambooth extension is better for sd 1.5
Fi will search best parameters for sd 1.5 too for kohya
Fafter sdxl dreambooth hopefully
Ldo you have best setting for dreambooth model SD 1,5? I have take a rtx3090 on runpod since I only have 12gb vram on my pc
Fi dont have yet sadly for kohya
Fit is on my research list
Fbut i have for extension
FLthanks was looking for dreambooth
F1 auto installer
F2 settings
LIs it compulsory to use class images?
Fnot but improves
Fi have class images too
Lwhy is there 2 links?
F1 settings
F1 auto installer
Fread all links
Lah ok thank you
Lwill go through it
AYes, I ran the --medvram-sdxl command and it really helped for my 3060 ti. The only downside is the long wait for the first image to be generated. Also xformers helped me because opt-sdp-attention gives extremely low generation speed for sdxl.
Fah u have ti
Fit has only 6 gb vram
N: ERROR Error while calling W&B API: user is not logged in (<Response [401]>)
Problem at: /workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/tracking.py 294 init
wandb: ERROR The API key is either invalid or missing, or the host is incorrect. To resolve this issue, you may try running the 'wandb login --host [hostname]' command. The host defaults to 'https://api.wandb.ai' if not specified. (Error 401: Unauthorized)
Traceback (most recent call last):
File "/workspace/kohya_ss/./train_db.py", line 481, in <module>
train(args)
File "/workspace/kohya_ss/./train_db.py", line 258, in train
accelerator.init_trackers("dreambooth" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs)
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 564, in _inner
return PartialState().on_main_process(function)(*args, kwargs)
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 2096, in init_trackers
self.trackers.append(tracker_init(project_name, init_kwargs.get(str(tracker), {})))
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/tracking.py", line 85, in execute_on_main_process
return function(self, *args, kwargs)
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/tracking.py", line 294, in init
self.run = wandb.init(project=self.run_name, kwargs)
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/wandb/sdk/wandb_init.py", line 1164, in init
raise e
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/wandb/sdk/wandb_init.py", line 1145, in init
run = wi.init()
File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/wandb/sdk/wandb_init.py", line 764, in init
raise error
wandb.errors.AuthenticationError: The API key is either invalid or missing, or the host is incorrect. To resolve this issue, you may try running the 'wandb login --host [hostname]' command. The host defaults to 'https://api.wandb.ai' if not specified. (Error 401: Unauthorized)
NI recently tried to start training in Kohya and I got that error, do you know what it could be?
Sis there anyway for me to run a seperate instance of automatic1111 so that i can have the old version with working dreambooth as well as a updated version @Dr. Furkan Gözükara
Fit says wan db api error
Finstall into a new folder
Fthats it
Sthank you, do you have a link to the latest installer?
Saslo did you ever find out if it was possble to run from an external hdd?
Fyes external hdd working
Fauto installer windows
SPerfect thank you
Myes of course, I mean in your video its was Dreambooth and Dreambooth lora ( exact name) maybe renamed to lora only in the newest version .