# HuggingFaceModel() Sagemaker invoke error in Stable Diffusion 2.1

**URL:** <https://discuss.huggingface.co/t/huggingfacemodel-sagemaker-invoke-error-in-stable-diffusion-2-1/131957>\
**Category:** Amazon SageMaker\
**Created:** [December 17, 2024, 8:27pm UTC](https://discuss.huggingface.co/t/huggingfacemodel-sagemaker-invoke-error-in-stable-diffusion-2-1/131957 "2024-12-17T20:27:17Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sanan](https://avatars.discourse-cdn.com/v4/letter/s/5fc32e/32.png) [@Sanan](https://discuss.huggingface.co/u/Sanan)\
**Post date:** [December 17, 2024, 8:27pm UTC](https://discuss.huggingface.co/t/huggingfacemodel-sagemaker-invoke-error-in-stable-diffusion-2-1/131957/1 "2024-12-17T20:27:17Z")

</div>

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](http://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?