# Hugging Face — Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive

- Company: Hugging Face (huggingface.co)
- Announced: 2024-01-15T00:00:00+00:00
- Subject: Platform
- Models affected: SD Turbo, SDXL Turbo
- Source: https://huggingface.co/blog/sdxl_ort_inference
- Record: https://forck.live/items/1958-accelerating-sd-turbo-and-sdxl-turbo-inference-with-onnx-runtime-and-olive

Hugging Face blog post describing how to accelerate SD Turbo and SDXL Turbo inference using ONNX Runtime and Olive, with performance benchmarks showing up to 229% throughput gains for SDXL Turbo and 120% for SD Turbo.

## Evidence

Verbatim from https://huggingface.co/blog/sdxl_ort_inference:

> ONNX Runtime outperformed PyTorch for all (batch size, number of steps) combinations tested, with throughput gains as high as 229% for the SDXL Turbo model and 120% for the SD Turbo model.

---

Record: https://forck.live/items/1958-accelerating-sd-turbo-and-sdxl-turbo-inference-with-onnx-runtime-and-olive
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md