python3 image_from_text.py --text='a comfy chair that looks like an avocado' --mega --seed=4
on a new local installation on macOS Monterey yields the following error:
detokenizing image
Traceback (most recent call last):
File "/Users/user/code/min-dalle/image_from_text.py", line 44, in <module>
image = generate_image_from_text(
File "/Users/user/code/min-dalle/min_dalle/generate_image.py", line 75, in generate_image_from_text
image = detokenize_torch(torch.tensor(image_tokens))
File "/Users/user/code/min-dalle/min_dalle/min_dalle_torch.py", line 108, in detokenize_torch
params = load_vqgan_torch_params(model_path)
File "/Users/user/code/min-dalle/min_dalle/load_params.py", line 12, in load_vqgan_torch_params
params: Dict[str, numpy.ndarray] = serialization.msgpack_restore(f.read())
File "/usr/local/lib/python3.9/site-packages/flax/serialization.py", line 350, in msgpack_restore
state_dict = msgpack.unpackb(
File "msgpack/_unpacker.pyx", line 201, in msgpack._cmsgpack.unpackb
msgpack.exceptions.ExtraData: unpack(b) received extra data.
Is anyone running the sample prompt successfully on Mac? It is unclear to me wether the error is library or data related. Has anyone a similar problem?
Trying to run the sample
python3 image_from_text.py --text='a comfy chair that looks like an avocado' --mega --seed=4
on a new local installation on macOS Monterey yields the following error:
Is anyone running the sample prompt successfully on Mac? It is unclear to me wether the error is library or data related. Has anyone a similar problem?