search

MrForExample / ComfyUI-3D-Pack

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
MIT License
2.21k stars 221 forks source link

unique3d issues #179

Closed yosun closed 3 months ago

yosun commented 3 months ago

Error occurred when executing CLIPVisionLoader:

join() argument must be str, bytes, or os.PathLike object, not 'NoneType'

File "/home/yosun/sources/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/home/yosun/sources/ComfyUI/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/yosun/sources/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "/home/yosun/sources/ComfyUI/nodes.py", line 889, in load_clip clip_path = folder_paths.get_full_path("clip_vision", clip_name) File "/home/yosun/sources/ComfyUI/folder_paths.py", line 179, in get_full_path filename = os.path.relpath(os.path.join("/", filename), "/") File "/home/yosun/miniconda3/envs/comfyui/lib/python3.10/posixpath.py", line 90, in join genericpath._check_arg_types('join', a, p) File "/home/yosun/miniconda3/envs/comfyui/lib/python3.10/genericpath.py", line 152, in _check_arg_types raise TypeError(f'{funcname}() argument must be str, bytes, or '

yosun commented 3 months ago

Error occurred when executing IPAdapterAdvanced:

Error(s) in loading state_dict for ImageProjModel: size mismatch for proj.weight: copying a param with shape torch.Size([3072, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 1280]).

File "/home/yosun/sources/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/home/yosun/sources/ComfyUI/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/yosun/sources/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "/home/yosun/sources/ComfyUI/custom_nodes/ComfyUI_IPAdapter_plus/IPAdapterPlus.py", line 763, in apply_ipadapter work_model, face_image = ipadapter_execute(work_model, ipadapter_model, clip_vision, ipa_args) File "/home/yosun/sources/ComfyUI/custom_nodes/ComfyUI_IPAdapter_plus/IPAdapterPlus.py", line 391, in ipadapter_execute ipa = IPAdapter( File "/home/yosun/sources/ComfyUI/custom_nodes/ComfyUI_IPAdapter_plus/IPAdapterPlus.py", line 70, in init self.image_proj_model.load_state_dict(ipadapter_model["image_proj"]) File "/home/yosun/miniconda3/envs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2189, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(

Duodecimus commented 2 months ago

A lot of the nodes that load things from file doesn't seem to check if the object loaded before trying to run code on them. Most times you see a nonetype error like this, it means the node couldn't find the thing it was told to load and plows forward with an empty variable.

Specifically, it's looking for the file 'CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors'