Model card
sdxl-turbo is a real-time text-to-image model from Stability AI that generates high-quality images in a single forward pass. Unlike traditional diffusion models that require multiple denoising steps, turbo uses a distilled approach to deliver fast inference without sacrificing detail. It integrates smoothly with the Hugging Face Diffusers library, making it accessible for developers already working in that ecosystem. Ideal for rapid prototyping, interactive applications, and use cases where speed matters more than absolute precision. While it produces fewer variations per prompt compared to full SDXL, it excels in scenarios needing quick iteration or live user feedback. As with any generative model, review the model card and license terms before deploying in production environments.
Model files and versions
Download this model
We recommend using the ModelScope CLI or SDK. Install ModelScope first, then choose a full snapshot, single file, SDK or Git LFS workflow.
stabilityai/sdxl-turboInstall the CLI and SDK dependency before downloading.
pip install modelscopeDownload the complete weights, configuration and model card.
modelscope download --model stabilityai/sdxl-turboREADME.md is used as an example; replace it with another repository file when needed.
modelscope download --model stabilityai/sdxl-turbo README.md --local_dir ./dirUseful in Python projects and automation scripts.
from modelscope import snapshot_download
model_dir = snapshot_download('stabilityai/sdxl-turbo')Make sure Git LFS is installed correctly.
git lfs install
git clone https://www.modelscope.cn/stabilityai/sdxl-turbo.gitFetch the repository structure first, then pull large files when needed.
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/stabilityai/sdxl-turbo.gitHow to use
- 01Step 1
Read the model card and source information.
- 02Step 2
Start with a small, non-sensitive evaluation.
- 03Step 3
Review quality, licensing and usage limits.
- 04Step 4
Adopt it only after validation.
Discussions
Use this space to keep checking source information, usage experience and maintenance status.
Open source page