Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Additional Network extension not installed, Only hijack built-in lora LoCon Extension hijack built-in lora successfully #11

Closed
randomuser11956 opened this issue Mar 18, 2023 · 1 comment

Comments

@randomuser11956
Copy link

Hello, i get this thing when i run stable diffusion webui and don't know what it means... Is it bad? Did something break?
All my loras work... well now, first all of the gave errors
"Error running process_batch: C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py
Traceback (most recent call last):
File "C:\Users\me\stable-diffusion-webui\modules\scripts.py", line 427, in process_batch
script.process_batch(p, *script_args, **kwargs)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py", line 209, in process_batch
network, info = lora_compvis.create_network_and_apply_compvis(du_state_dict, weight_tenc, weight_unet, text_encoder, unet)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 102, in create_network_and_apply_compvis
state_dict = network.apply_lora_modules(du_state_dict) # some weights are applied to text encoder
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 289, in apply_lora_modules
state_dict = LoRANetworkCompvis.convert_state_dict_name_to_compvis(self.v2, du_state_dict)
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 193, in convert_state_dict_name_to_compvis
compvis_name = LoRANetworkCompvis.convert_diffusers_name_to_compvis(v2, tokens[0])
File "C:\Users\me\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 182, in convert_diffusers_name_to_compvis
assert cv_name is not None, f"conversion failed: {du_name}. the model may not be trained by sd-scripts."
AssertionError: conversion failed: lora_unetdown"
-this was the error i was getting when trying to use loras

but afterwards i used git pull command in the extension folder and my loras still did not work
then i used pip install -r requirements.txt in the sd folder
after this install i managed to make my loras work. BUT i still get this thing in my command prompt when i run sd
loras work when i enable them in the additional networks drop down menu

this happened when i updated to torch 2 and changed some requirements like accelerate and transformers version.
now i have xformers==0.0.17.dev476, torch: 1.13.1+cu117 and transformers==4.25.1 accelerate==0.12.0

now loras work but when i open sd webui i get that thing that is in the title.

@KohakuBlueleaf
Copy link
Owner

@randomuser11956 It looks like all the error you got is from addnet extension, and since I already remove all the hook for addnet. You may want to send this issue to kohya_ss.
And if you are trying to use LoCon/LoHa in the addnet it is normal to get some error. (not supported now, only non-cp decomposition LoCon can be used in addnet)

(the hook for addnet will add back in the future if I figure out how to hook new addnet extension)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants