|
--- |
|
pipeline_tag: text-to-image |
|
library_name: optimum_neuronx |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
--- |
|
|
|
This is a model compiled for optimized inference on AWS inf2 instances. The overall performance can achieve 4it/s for a 1024x1024 picture. |
|
|
|
NOTE: In order to load and infer on inf2.xlarge instances, a minimum of 8 GB SWAP memory is required. Other instance sizes do not require this. |
|
|
|
Assuming you're using the official DLAMI or installed the drivers and libraries required for neuron devices, install the latest optimum_neuronx library: |
|
``` |
|
pip install -U optimum[neuronx] diffusers=0.20.0 |
|
``` |
|
|
|
Then, enjoy the super-fast experience: |
|
```py |
|
from optimum.neuron import NeuronStableDiffusionXLPipeline |
|
pipe = NeuronStableDiffusionXLPipeline.from_pretrained("paulkm/sdxl_neuron_pipe", device_ids=[0,1]) |
|
img = pipe("a cute black cat").images[0] |
|
``` |
