Sdxl turbo
Model Overview¶
SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.
SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis. SDXL-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.
- Developed by: Stability AI
- Model type: Generative text-to-image model
- Repository: Stability-AI/generative-models
- Paper: Stability-AI/adversarial-diffusion-distillation
QPC Configurations¶
| Model Name | Cores | Generated URL | Download |
|---|---|---|---|
| sdxl-turbo | 16 | https://dc00tk1pxen80.cloudfront.net/SDK1.19.6/sdxl_turbo/compiled-bin-fp16-B1-C2-A7-best-throughput.tar.gz | Download |