utils\util_image.py:269: RuntimeWarning: invalid value encountered in cast img_np = img_np.astype(out_type)

[puppyjuan]

Hello author！
I run app.py and test using http://127.0.0.1:7860/. After I submit "Low Quality Image" using the sample image, I get a black "High Quality Image". The console output utils\util_image.py:269: RuntimeWarning: invalid value encountered in cast img_np = img_np.astype(out_type).
When I debug and step into util_image.py line 269, I found that the "img_np" value is all nan.
Can you help me with this problem? Thanks very much！

Bellow is the entire console output:
C:\ProgramData\Anaconda3\envs\resshift\python.exe D:/project2/ResShift_Efficient_Diffusion_Model_2023/app.py
D:\project2\ResShift_Efficient_Diffusion_Model_2023\app.py:192: GradioDeprecationWarning: Usage of gradio.outputs is deprecated, and will not be supported in the future, please import your components from gradio.components
gr.outputs.File(label="Download the output")
Running on local URL: http://127.0.0.1:7860
IMPORTANT: You are using gradio version 3.50.0, however version 4.44.1 is available, please upgrade.

Running on public URL: https://260c8f8a2b9875daf6.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run gradio deploy from Terminal to deploy to Spaces (https://huggingface.co/spaces)
Building the diffusion model with length: 4...
C:\ProgramData\Anaconda3\envs\resshift\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3527.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Loading Diffusion model from weights\resshift_bicsrx4_s4.pth...
building MemoryEfficientAttnBlock with 512 in_channels...
Working with z of shape (1, 3, 64, 64) = 12288 dimensions.
building MemoryEfficientAttnBlock with 512 in_channels...
Loading AutoEncoder model from weights\autoencoder_vq_f4.pth...
D:\project2\ResShift_Efficient_Diffusion_Model_2023\utils\util_image.py:269: RuntimeWarning: invalid value encountered in cast
img_np = img_np.astype(out_type)
Processing done, enjoy the results in restored_output