A double download problem
Hi, I made different colabs to use Stable Cascade, and I get bugs:
In this one, I get this:
AttributeError Traceback (most recent call last)
in <cell line: 15>()
13 prior_model_id = "stabilityai/stable-cascade-prior"
14 decoder_model_id = "stabilityai/stable-cascade"
---> 15 prior = StableCascadePriorPipeline.from_pretrained(prior_model_id, torch_dtype=torch.bfloat16).to(device)
16 decoder = StableCascadeDecoderPipeline.from_pretrained(decoder_model_id, torch_dtype=torch.float16).to(device)
17
4 frames
/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py in getattr(self, name)
695 value = getattr(module, name)
696 else:
--> 697 raise AttributeError(f"module {self.name} has no attribute {name}")
698
699 setattr(self, name, value)
AttributeError: module diffusers has no attribute StableCascadeUNet
And in a more recent colab, I get very slow downloads for safetensor, something like one hour DL:
diffusion_pytorch_model.safetensors: 1%
83.9M/14.4G [00:23<58:50, 4.04MB/s]
Is there something I miss? I'm sad, because Cascade is really great!