-
Notifications
You must be signed in to change notification settings - Fork 29
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
Issue in file EchoMimic_node.py #34
Comments
I am modifying the code, please try the latest version |
Thanks, sure will update !! |
I can't see the image you sent, but the error message you submitted shows that the image was cropped incorrectly. What is the size setting for your image |
It worked, thanks. I have one more query. Right now face is getting cropped and output is that cropped face. What are the parameters which needs to be cahnged to get it applied on complete input image. Turning face-crop dont work. |
"crop_face" turn on and " crop_face_ratio "to 0.99, if using pose ,motion_sync 's base video also need a half body |
_upsample_nearest_exact2d() received an invalid combination of arguments - got (Tensor, tuple, NoneType), but expected one of:
didn't match because some of the arguments have invalid types: (�[32;1mTensor�[0m, �[31;1mtuple of (bool, int)�[0m, �[31;1mNoneType�[0m)
File "/data/ComfyUI/execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/data/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 "/data/ComfyUI/execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/data/ComfyUI/custom_nodes/ComfyUI_EchoMimic/EchoMimic_node.py", line 631, in em_main
image=nomarl_upscale(image,width, height)
File "/data/ComfyUI/custom_nodes/ComfyUI_EchoMimic/EchoMimic_node.py", line 314, in nomarl_upscale
img = common_upscale(samples, width, height, "nearest-exact", "center")
File "/data/ComfyUI/comfy/utils.py", line 575, in common_upscale
return torch.nn.functional.interpolate(s, size=(height, width), mode=upscale_method)
File "/root/anaconda3/lib/python3.10/site-packages/torch/nn/functional.py", line 4008, in interpolate
return torch._C._nn._upsample_nearest_exact2d(input, output_size, scale_factors)
The text was updated successfully, but these errors were encountered: