Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive

Stability AI announced the integration of ONNX Runtime and Olive to accelerate the inference of their SD Turbo and SDXL Turbo models. This optimization leverages model quantization and graph optimization techniques, enhancing performance on various hardware platforms. Practitioners can expect improved inference speeds and reduced latency when deploying these models in production environments, facilitating more efficient use of resources.