Stable diffusion xl base 1.0
Model Overview¶
SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model specialized for the final denoising steps. Note that the base model can be used as a standalone module.
Stable-diffusion-xl-base-1.0 model can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).
- Developed by: Stability AI
- Model type: Generative text-to-image model
- License: CreativeML Open RAIL++-M License
- Repository: stabilityai/stable-diffusion-xl-base-1.0
- Paper: SDXL report on arXiv
QPC Configurations¶
| Model Name | Cores | Generated URL | Download | Generation Date |
|---|---|---|---|---|
| stable-diffusion-xl-base-1.0 | 16 | https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/stabilityai/stable-diffusion-xl-base-1.0/stable_diffusion_xl_base_1_0_qpc_16cores.tar.gz | Download | 27-Jan-2026 |