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 Zoe-DepthMapPreprocessor #2

Closed
rovo79 opened this issue Aug 17, 2023 · 22 comments
Closed

Error occurred when executing Zoe-DepthMapPreprocessor #2

rovo79 opened this issue Aug 17, 2023 · 22 comments

Comments

@rovo79
Copy link

rovo79 commented Aug 17, 2023

Running this on Mac OS with MPS support in nightly Pytorch.

!!! Exception during processing !!!
Traceback (most recent call last):
  File "~/ComfyUI/execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "~/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 "~/ComfyUI/execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/zoe.py", line 18, in execute
    return (common_annotator_call(model, image), )
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/utils.py", line 28, in common_annotator_call
    np_result = model(np_image, output_type="numpy", **kwargs)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/__init__.py", line 56, in __call__
    depth = self.model.infer(image_depth)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 126, in infer
    return self.infer_with_flip_aug(x, pad_input=pad_input, **kwargs)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 110, in infer_with_flip_aug
    out = self._infer_with_pad_aug(x, pad_input=pad_input, **kwargs)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 88, in _infer_with_pad_aug
    out = self._infer(x)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 55, in _infer
    return self(x)['metric_depth']
  File "~/.pyenv/versions/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "~/.pyenv/versions/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/zoedepth/zoedepth_v1.py", line 144, in forward
    rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
  File "~/.pyenv/versions/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "~/.pyenv/versions/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 263, in forward
    x = self.prep(x)
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 187, in __call__
    return self.normalization(self.resizer(x))
  File "~/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 174, in __call__
    return nn.functional.interpolate(x, (height, width), mode='bilinear', align_corners=True)
  File "~/.pyenv/versions/comfyui/lib/python3.10/site-packages/torch/nn/functional.py", line 3926, in interpolate
    raise TypeError(
TypeError: expected size to be one of int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int], but got size with types [<class 'numpy.int64'>, <class 'numpy.int64'>]

I have no idea if this is related but noticed that in:
custom_nodes/comfyui_controlnet_aux/node_wrappers/zoe.py

it can't import
import controlnet_aux

More likely I'm thinking this must have something to do with the way torch is casting integers.

@Fannovel16
Copy link
Owner

Fannovel16 commented Aug 17, 2023

I just tested on ComfyUI_windows_portable and couldn't reproduce that bug. It seems to be a MPS-specific bug like you said.

@Fannovel16
Copy link
Owner

Can you try to upgrade pytorch to the newest version? This bug come from the pytorch side so if that doesn't work then I will just force it to use the CPU if the device is MPS.

@rovo79
Copy link
Author

rovo79 commented Aug 17, 2023

Thanks for testing it out.
I am upgraded to the latest nightly PyTorch.
I usually run comfyui with "--force-fp16" argument. I also tried "--force-fp32" just incase, but didn't have an effect.

My work-around at the moment was to disconnect the Zoe depth and put in place a Midas depth. I don't know what I'm doing, but so far it seems to be working.

image

@Lightsockie
Copy link

I used to get a similar issue to the one in the OP, but uninstalling https://github.com/space-nuko/ComfyUI-Disco-Diffusion resolved it for me. Might check for any potential conflicts with other custom nodes (especially if you have this one).

@Fannovel16
Copy link
Owner

I used to get a similar issue to the one in the OP, but uninstalling https://github.com/space-nuko/ComfyUI-Disco-Diffusion resolved it for me. Might check for any potential conflicts with other custom nodes (especially if you have this one).

I think the source of this issue is that midas_repo import "midas" which seems to conflict with "midas" from other repos

@Fannovel16
Copy link
Owner

Can you guys test the new commit? I moved midas_repo to different location and rename stuffs midas.dpt_depth to custom_midas_repo.midas.depth to avoid conflicts.
adbce8d

@Lightsockie
Copy link

I think I actually can't retest this repo's Zoe-DepthMapPreprocessor until #3 is resolved. I resolved this issue with this preproc on the old repo by removing that conflicting custom_node provider. Here's my error for posterity:

KeyError: 'Zoe-DepthMapPreprocessor'
got prompt
Error handling request
Traceback (most recent call last):
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/venv/lib/python3.11/site-packages/aiohttp/web_protocol.py", line 433, in _handle_request
    resp = await request_handler(request)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/venv/lib/python3.11/site-packages/aiohttp/web_app.py", line 504, in _handle
    resp = await handler(request)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/venv/lib/python3.11/site-packages/aiohttp/web_middlewares.py", line 117, in impl
    return await handler(request)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/server.py", line 42, in cache_control
    response: web.Response = await handler(request)
                             ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/server.py", line 442, in post_prompt
    valid = execution.validate_prompt(prompt)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/gabriel/Work/StableDiffusion/ComfyUI/execution.py", line 596, in validate_prompt
    class_ = nodes.NODE_CLASS_MAPPINGS[prompt[x]['class_type']]
             ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: 'Zoe-DepthMapPreprocessor'

Currently on commit 2a0ee39
I'm using your provided test workflow from here, btw: https://github.com/Fannovel16/comfyui_controlnet_aux/blob/main/tests/test_cn_aux_full.json
(which seems to be looking for missing "LeReS-DepthMapPreprocessor" & "DWPreprocessor" custom nodes, btw)

@Fannovel16
Copy link
Owner

@Lightsockie I fixed #3. Can you try again?

@KevinParnell
Copy link

KevinParnell commented Aug 20, 2023

Up to date as of earlier this evening and receiving pretty much the same issue
`Error occurred when executing Zoe-DepthMapPreprocessor:

expected size to be one of int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int], but got size with types [, ]

File "F:\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "F:\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 "F:\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\zoe.py", line 18, in execute
return (common_annotator_call(model, image), )
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\utils.py", line 28, in common_annotator_call
np_result = model(np_image, output_type="numpy", **kwargs)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe_init_.py", line 56, in call
depth = self.model.infer(image_depth)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\depth_model.py", line 126, in infer
return self.infer_with_flip_aug(x, pad_input=pad_input, **kwargs)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\depth_model.py", line 110, in infer_with_flip_aug
out = self._infer_with_pad_aug(x, pad_input=pad_input, **kwargs)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\depth_model.py", line 88, in _infer_with_pad_aug
out = self._infer(x)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\depth_model.py", line 55, in _infer
return self(x)['metric_depth']
File "F:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "F:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\zoedepth\zoedepth_v1.py", line 144, in forward
rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
File "F:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "F:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\base_models\midas.py", line 263, in forward
x = self.prep(x)
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\base_models\midas.py", line 187, in call
return self.normalization(self.resizer(x))
File "F:\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\zoe\zoedepth\models\base_models\midas.py", line 174, in call
return nn.functional.interpolate(x, (height, width), mode='bilinear', align_corners=True)
File "F:\ComfyUI\venv\lib\site-packages\torch\nn\functional.py", line 3926, in interpolate
raise TypeError(`

pytorch is also up to date on the nightly channel, using cuda 12.1 and bf16 flag in comfy

@bissigb
Copy link

bissigb commented Aug 20, 2023

Hi,
i dont work an Mac, but had similar issues on Win with colab (as others had). Fixed it with the new repo https://github.com/Fannovel16/comfyui_controlnet_aux

@Pedroman1
Copy link

Pedroman1 commented Aug 21, 2023

same issue as @KevinParnell

@Lightsockie
Copy link

Lightsockie commented Aug 21, 2023

@Lightsockie fixed #3. Can you try again?

Sorry about the delay, but confirming issue still exists. Only using this custom_node and ComfyUI-Manager
comfy: bc76b3829f5fbba7c5a439c7833d313a3ca87398
ComfyUI-Manager: 284e90dc8296a2e1e4f14b4b2d10fba2f52f0e53
control_aux: f99b09b

Same error as OP.

Python 3.11.3
torch==2.1.0.dev20230726+rocm5.6
torchaudio==2.1.0.dev20230727+rocm5.6
torchvision==0.16.0.dev20230727+rocm5.6

Also worth mentioning is around the time that when you did this

I think the source of this issue is that midas_repo import "midas" which seems to conflict with "midas" from other repos

I think you broke "compatibility" with with the old repo's Zoe. I had to disable custom_aux in my "real" install to have the old Zoe custom node work again. Won't matter once we get this new sexy workin' but figured I'd mention it

jk I see the README now says not to do this

@kameleo333
Copy link

Hi M1max64go here I get this :
Error occurred when executing Zoe-DepthMapPreprocessor:

expected size to be one of int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int], but got size with types [, ]

File "/Users/gbkm1max/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/Users/gbkm1max/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 "/Users/gbkm1max/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/zoe.py", line 19, in execute
out = common_annotator_call(model, image)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/utils.py", line 28, in common_annotator_call
np_result = model(np_image, output_type="np", **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/init.py", line 56, in call
depth = self.model.infer(image_depth)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 126, in infer
return self.infer_with_flip_aug(x, pad_input=pad_input, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 110, in infer_with_flip_aug
out = self._infer_with_pad_aug(x, pad_input=pad_input, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 88, in _infer_with_pad_aug
out = self._infer(x)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 55, in _infer
return self(x)['metric_depth']
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/zoedepth/zoedepth_v1.py", line 144, in forward
rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 265, in forward
x = self.prep(x)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 189, in call
return self.normalization(self.resizer(x))
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py", line 176, in call
return nn.functional.interpolate(x, (height, width), mode='bilinear', align_corners=True)
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/functional.py", line 3926, in interpolate
raise TypeError(

@gnadenlos
Copy link

Same error on Windows 11 with Python 3.11.6 and torch 2.1.0+cu121.

@cubiq
Copy link

cubiq commented Oct 8, 2023

this also happens on linux/cuda

to fix this:
file /comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py replace line 176 with

return nn.functional.interpolate(x, (int(height), int(width)), mode='bilinear', align_corners=True)

file /comfyui_controlnet_aux/src/custom_midas_repo/midas/backbones/beit.py replace line 47 with

new_sub_table = F.interpolate(old_sub_table, size=(int(new_height), int(new_width)), mode="bilinear")

@JPS-GER
Copy link

JPS-GER commented Oct 8, 2023

to fix this

Your fix worked for me. Thanks.

@JxinBain
Copy link

JxinBain commented Oct 12, 2023

to fix this

Your fix worked for me. Thanks.

it does worked in windows alse.can you merge it to the main branch.

@SuperUserNameMan
Copy link

@cubiq : thank for the fix.

No one willing to create a PR ?

@cubiq
Copy link

cubiq commented Oct 13, 2023

PR #71 pushed

@kameleo333
Copy link

this also happens on linux/cuda

to fix this: file /comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/base_models/midas.py replace line 176 with

return nn.functional.interpolate(x, (int(height), int(width)), mode='bilinear', align_corners=True)

file /comfyui_controlnet_aux/src/custom_midas_repo/midas/backbones/beit.py replace line 47 with

new_sub_table = F.interpolate(old_sub_table, size=(int(new_height), int(new_width)), mode="bilinear")
Tried you code change and now I get this (M1Max64go) :

Error occurred when executing Zoe-DepthMapPreprocessor:

The operator 'aten::upsample_bicubic2d.out' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on pytorch/pytorch#77764. As a temporary fix, you can set the environment variable PYTORCH_ENABLE_MPS_FALLBACK=1 to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.

File "/Users/gbkm1max/ComfyUI/execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/Users/gbkm1max/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 "/Users/gbkm1max/ComfyUI/execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/zoe.py", line 19, in execute
out = common_annotator_call(model, image)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/utils.py", line 28, in common_annotator_call
np_result = model(np_image, output_type="np", **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/init.py", line 56, in call
depth = self.model.infer(image_depth)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 126, in infer
return self.infer_with_flip_aug(x, pad_input=pad_input, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 110, in infer_with_flip_aug
out = self._infer_with_pad_aug(x, pad_input=pad_input, **kwargs)
File "/Users/gbkm1max/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/zoe/zoedepth/models/depth_model.py", line 90, in _infer_with_pad_aug
out = F.interpolate(out, size=(x.shape[2], x.shape[3]), mode=upsampling_mode, align_corners=False)
File "/Users/gbkm1max/.pyenv/versions/3.9.2/lib/python3.9/site-packages/torch/nn/functional.py", line 4030, in interpolate
return torch._C._nn.upsample_bicubic2d(input, output_size, align_corners, scale_factors)

@Fannovel16
Copy link
Owner

@kameleo333 Fixed at e3ac5ef

Fannovel16 added a commit that referenced this issue Oct 18, 2023
Fannovel16 added a commit that referenced this issue Oct 18, 2023
Fannovel16 added a commit that referenced this issue Oct 21, 2023
@WWddf112112313
Copy link

Error occurred when executing MiDaS-DepthMapPreprocessor:

Connection error, and we cannot find the requested files in the disk cache. Please try again or make sure your Internet connection is on.

File "I:\Blender_ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "I:\Blender_ComfyUI\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "I:\Blender_ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "I:\Blender_ComfyUI\ComfyUI\custom_nodes\comfyui_controlnet_aux-main\node_wrappers\midas.py", line 45, in execute
model = MidasDetector.from_pretrained(HF_MODEL_NAME, cache_dir=annotator_ckpts_path).to(model_management.get_torch_device())
File "I:\Blender_ComfyUI\ComfyUI\custom_nodes\comfyui_controlnet_aux-main\src\controlnet_aux\midas_init_.py", line 28, in from_pretrained
model_path = hf_hub_download(pretrained_model_or_path, filename, cache_dir=cache_dir)
File "I:\Blender_ComfyUI\python_embeded\lib\site-packages\huggingface_hub\utils_validators.py", line 120, in _inner_fn
return fn(*args, **kwargs)
File "I:\Blender_ComfyUI\python_embeded\lib\site-packages\huggingface_hub\file_download.py", line 1227, in hf_hub_download
raise LocalEntryNotFoundError(

Close

Fannovel16 pushed a commit that referenced this issue Nov 5, 2023
add config path judge, change default annotator_ckpts_path consistent with utils.py
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