lllyasviel / lllyasviel/stable-diffusion-webui-forge

[Bug]: Lora can't load

Open
#452 1 comment 1 reaction 0 assignees View on GitHub
Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

### Checklist

- [ ] The issue exists after disabling all extensions
- [ ] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [ ] The issue exists in the current version of the webui
- [X] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

Lora is not working when loading from google drive

Traceback (most recent call last):
File "/content/webui-forge/extensions-builtin/Lora/networks.py", line 279, in load_networks
net = load_network(name, network_on_disk)
File "/content/webui-forge/extensions-builtin/Lora/networks.py", line 218, in load_network
net_module = nettype.create_module(net, weights)
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 11, in create_module
return NetworkModuleLora(net, weights)
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 20, in __init__
self.up_model = self.create_module(weights.w, "lora_up.weight")
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 51, in create_module
raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
AssertionError: Lora layer lora_te_text_model_encoder_layers_0_mlp_fc1.alpha matched a layer with unsupported type: Linear

### Steps to reproduce the problem

1

### What should have happened?

1

### What browsers do you use to access the UI ?

Mozilla Firefox

### Sysinfo

Tesla T4

### Console logs

```Shell
Traceback (most recent call last):
File "/content/webui-forge/extensions-builtin/Lora/networks.py", line 279, in load_networks
net = load_network(name, network_on_disk)
File "/content/webui-forge/extensions-builtin/Lora/networks.py", line 218, in load_network
net_module = nettype.create_module(net, weights)
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 11, in create_module
return NetworkModuleLora(net, weights)
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 20, in __init__
self.up_model = self.create_module(weights.w, "lora_up.weight")
File "/content/webui-forge/extensions-builtin/Lora/network_lora.py", line 51, in create_module
raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
AssertionError: Lora layer lora_te_text_model_encoder_layers_0_mlp_fc1.alpha matched a layer with unsupported type: Linear
```

### Additional information

_No response_

Contributor guide

No contributing guide indexed for this repository

Research direction

Start in extensions-builtin/Lora/networks.py and extensions-builtin/Lora/network_lora.py, following the load_network and create_module paths shown in the traceback. Reproduce the failure while loading the LoRA from Google Drive and inspect why the text-encoder layer is treated as an unsupported Linear type. Done means the LoRA loads without this assertion.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.