Spaces:
Running
on
Zero
Running
on
Zero
Something's broken
#16
by
FireCat1
- opened
Now shows an error lozenge after several seconds. Any prompt. Possibly related to what I started seeing today on my private clone of this space:
Traceback (most recent call last):
File "/home/user/app/app.py", line 67, in <module>
prior_pipeline = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", torch_dtype=dtype)#.to(device)
File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
return fn(*args, **kwargs)
File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 1264, in from_pretrained
loaded_sub_model = load_sub_model(
File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 443, in load_sub_model
class_obj, class_candidates = get_class_obj_and_candidates(
File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 347, in get_class_obj_and_candidates
class_obj = getattr(library, class_name)
File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/utils/import_utils.py", line 697, in __getattr__
raise AttributeError(f"module {self.__name__} has no attribute {name}")
AttributeError: module diffusers has no attribute StableCascadeUNet
oh I have same issues @@
I have same issues
@multimodalart Any solution in sight?
if you are using diffusers from https://github.com/kashif/diffusers@a3dc21385b7386beb3dab3a9845962ede6765887 or https://github.com/kashif/diffusers@wuerstchen-v3 you can either
- remove this dependency and replace it with latest diffusers (check out https://huggingface.co/spaces/multimodalart/stable-cascade/commit/d44748651631aeef8d32910bf82f752280d41685)
OR - update the revision ids when using
from_pretrainedas below
StableCascadePriorPipeline.from_pretrained(
"stabilityai/stable-cascade-prior",
torch_dtype=torch.bfloat16,
revision="621fc2ddab5500e57079e716c15358a25b649090",
)
StableCascadeDecoderPipeline.from_pretrained(
"stabilityai/stable-cascade",
torch_dtype=torch.float16,
revision="e3aee2fd11a00865f5c085d3e741f2e51aef12d3",
)
Hey folks, having the same problem.
Please could you explain the process in a little more detail. I dont understand alot of the terminology above so im a bit stumped.
Would really appreciate any assistance.