How to Deploy HuggingFace’s Stable Diffusion Pipeline with Triton Inference Server

This video showcases deploying the Stable Diffusion pipeline available through the HuggingFace diffuser library. We use Triton Inference Server to deploy and run the pipeline. Two models in the pipeline have been exported to ONNX and TensorRT to demonstrate use of multiple backends in the same pipeline.

Note: This example doesn’t include all possible optimizations to the stable diffusion pipeline. The intent is to show ease of deployment with Triton.

#ai #inference #triton #deeplearning #stablediffusion

[random_sinner]

I can hear this voice in my head every time I code now. So lovely!

[bulgingbattery]

If only stable diffusion had a YottaFLOP supercomputer.

[phiai]

Here are ste-by-step walkthouroughs how to:
1. Generate deployable models for PyTorch ResNet50 using Nvidia PyTorch Container

2. Deploy PyTorch ResNet50 model on AWS SageMaker using Nvidia Triton Inference Server

[Tymczas]

are you so cheap to hire Indian guy only? Nvidia is broke...lol