search

tiankuan93 / ComfyUI-V-Express

86 stars 9 forks source link

V-Express Features Not Working in Interface #3

Closed M4K4R closed 3 weeks ago

M4K4R commented 1 month ago

Description: I have installed the ComfyUI-V-Express repository on my ComfyUI server hosted on Huggingface. However, I am unable to use some features related to V-Express in the interface. Options like "Set V-Express Model Path" are not functioning. I need assistance to resolve this issue. I have attached a screenshot for reference.

Steps to Reproduce:

  1. Install the ComfyUI-V-Express repository on a ComfyUI server hosted on Huggingface.
  2. Navigate to the interface section.
  3. Attempt to use options like "Set V-Express Model Path" from the menu.

Expected Behavior: These options should work, allowing paths to be set without issues.

Actual Behavior: These options are non-functional. Settings cannot be applied or saved.

Additional Information:

Can you provide guidance on how to resolve this issue? Thank you for your help.

tiankuan93 commented 1 month ago

I'm not sure if this has anything to do with the name of the node. To avoid potential risks, I updated some of the node names to make them more reasonable. You can pull the latest repository and workflow to try it.

M4K4R commented 1 month ago

Thank you for the prompt update. I have pulled the latest repository and workflow, which resolved the initial issue. However, I am now encountering a new error when executing V-Express_Loader.

The error message is:

Error occurred when executing V_Express_Loader:

We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like /home/user/app/custom_nodes/ComfyUI-V-Express/model_ckpts/stable-diffusion-v1-5/unet/config.json is not the path to a directory containing a config.json file.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

File "/home/user/app/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/user/app/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/home/user/app/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/user/app/custom_nodes/ComfyUI-V-Express/nodes.py", line 324, in load_vexpress_pipeline reference_net = load_reference_net(unet_config_path, reference_net_path, dtype, device)
File "/home/user/app/custom_nodes/ComfyUI-V-Express/src/inference.py", line 69, in load_reference_net reference_net = UNet2DConditionModel.from_config(unet_config_path).to(dtype=dtype, device=device)
File "/home/user/.pyenv/versions/3.10.12/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 241, in from_config config, kwargs = cls.load_config(pretrained_model_name_or_path=config, return_unused_kwargs=True, **kwargs)
File "/home/user/.pyenv/versions/3.10.12/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 407, in load_config raise EnvironmentError

I'm unsure if this issue is related to my configuration or if it's something else.

tiankuan93 commented 1 month ago

It looks like you didn't download all the models. You need to download the model according to the installation and put it in the correct path.