Hello,
I deployed stabilityai/stable-diffusion-2-1 model on Sagemaker for text to image task however when I use invoke for getting output I receive following error:
File “/app/main.py”, line 265, in
invoke_model
response =
sagemaker_runtime.invoke_endpoint(
File
“/usr/local/lib/python3.9/site-packages
/botocore/client.py”, line 569, in
_api_call
return
self._make_api_call(operation_name,
kwargs)
File
“/usr/local/lib/python3.9/site-packages
/botocore/client.py”, line 1023, in
_make_api_call
raise error_class(parsed_response,
operation_name)
botocore.errorfactory.ModelError: An
error occurred (ModelError) when
calling the InvokeEndpoint operation:
Received client error (400) from
primary with message "{
“code”: 400,
“type”: “InternalServerException”,
“message”: “Cannot copy out of meta
tensor; no data!”
}
it is part of my deployment script:
hub = {
‘HF_MODEL_ID’: ‘stabilityai/stable-diffusion-2-1’, # model_id from hf.co/models
‘HF_TASK’: ‘text-to-image’
}
huggingface_model = HuggingFaceModel(
env = hub, # No pre-packaged model.tar.gz needed for built-in models
transformers_version=“4.26”, # Specify Transformers version
pytorch_version=“1.13”, # Specify PyTorch version
py_version=“py39”, # Python version
role= MY_ARN,
sagemaker_session = sagemaker_session
)
predictor = huggingface_model.deploy(
initial_instance_count=1, # Number of instances
instance_type= ‘ml.g4dn.2xlarge’
endpoint_name = job_name
)
My payload for invoke:
{
“inputs”: Descption_of_image
}
If you have any experience, could you please share?