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

Error occurred when executing T5TextEncode #ELLA: #58

Open
jinwen36 opened this issue Aug 9, 2024 · 10 comments
Open

Error occurred when executing T5TextEncode #ELLA: #58

jinwen36 opened this issue Aug 9, 2024 · 10 comments

Comments

@jinwen36
Copy link

jinwen36 commented Aug 9, 2024

Error occurred when executing T5TextEncode #ELLA:

property 'device' of 'T5EncoderModel' object has no setter

File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\custom_nodes\ComfyUI-ELLA\ella.py", line 228, in encode
cond = text_encoder_model(text, max_length=max_length)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\custom_nodes\ComfyUI-ELLA\model.py", line 136, in call
self.load_model()
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\custom_nodes\ComfyUI-ELLA\model.py", line 132, in load_model
model_management.load_model_gpu(self.patcher)
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\comfy\model_management.py", line 474, in load_model_gpu
return load_models_gpu([model])
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\comfy\model_management.py", line 468, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\comfy\model_management.py", line 296, in model_load
self.model.unpatch_model(self.model.offload_device)
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\comfy\model_patcher.py", line 556, in unpatch_model
self.model.device = device_to
^^^^^^^^^^^^^^^^^
File "C:\Users\jinwen\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1788, in setattr
super().setattr(name, value)

@extripod
Copy link

yes, i have same error today, yesterday everything is good.

@lin2012li
Copy link

lin2012li commented Aug 11, 2024

是因为更新了最新版的comfyui,不是ELLA插件问题,comfyui 升级后导致这个问题。退回以前版本就可以使用了。

@ElSuccerro
Copy link

same error here...

@exinnocommon
Copy link

I'm struggling with the same error. Please fix it so that it can be used in the latest version of ComfyUI.

@DB1052
Copy link

DB1052 commented Aug 14, 2024

Man, I really hope Ella isn’t dead. I really don’t want to roll back Comfy with all the new stuff being added.

@JettHu
Copy link
Collaborator

JettHu commented Aug 14, 2024

I'll try to fix this problem when I have time, in the next two days.

@JettHu
Copy link
Collaborator

JettHu commented Aug 16, 2024

fixed

@ElSuccerro
Copy link

Thanks!

@DB1052
Copy link

DB1052 commented Aug 16, 2024

fixed

Thank you!

@andupotorac
Copy link

It works, thanks!

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

8 participants