AttributeError: 'NoneType' object has no attribute '__array_interface__'

[IvanWaldon]

_Traceback (most recent call last):
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/gradio/routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/gradio/blocks.py", line 1435, in process_api
result = await self.call_function(
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/gradio/blocks.py", line 1107, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2505, in run_sync_in_worker_thread
return await future
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 1005, in run
result = context.run(func, *args)
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/gradio/utils.py", line 707, in wrapper
response = f(*args, **kwargs)
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/torch/utils/contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/oem/Downloads/Janus-main/demo/app_januspro.py", line 58, in multimodal_understanding
pil_images = [Image.fromarray(image)]
File "/home/oem/anaconda3/envs/sovits/lib/python3.9/site-packages/PIL/Image.py", line 2982, in fromarray
arr = obj.array_interface
AttributeError: 'NoneType' object has no attribute 'array_interface'

torch 2.5.1+ROCm6.2
GPU: AMD Radeon RX6600

I wonder it's wrong with torch or gradio and how can I deal with it?

[IvanWaldon]

For my vram is not large enough to load the model, I tried to load it with arg "dtype=torch.float16", but when I loaded it on CPU, I met the same problem too.