Support Knowledge Base

Encountered Error When Running Sdxl Turbo Model With Openvino™ GenAI

Content Type: Troubleshooting | Article ID: 000101202 | Last Reviewed: 05/22/2025

Description Resolution

Description

Ran SDXL Turbo Model with OpenVINO™ GenAI.
Encountered error:
RuntimeError :- Check ov_tokenizer || ov_detokenizer
Neither tokenizer nor detokenizer models were provided

Install required prerequisites:
pip install diffusers transformers accelerate --upgrade
Download and convert SDXL Turbo model into Intermediate Representation (IR):
optimum-cli export openvino -m stabilityai/sdxl-turbo sdxl-turbo
Run SDXL Turbo Model with OpenVINO GenAI:
import openvino_genai as og

from PIL import Image

pipeline=og.Text2ImagePipeline ("sdxl-vino","CPU")

This article applies to 3 products.

Intel® Xeon Phi™ Processor Software OpenVINO™ toolkit Performance Libraries

Contact support