SDXL Turbo是SDXL 1.0的极速版本，出图速度超快。这个版本是全精度版本，非常好用，画面相比半精度更不容易出错！SDXL Turbo基于一种称为对抗性扩散蒸馏（ADD）的新训练方法（见技术报告论文），该方法允许在1到4个步骤中以高图像质量对大规模基础图像扩散模型进行采样。这种方法使用分数蒸馏来利用大规模现成的图像扩散模型作为教学信号，并将其与对抗性损失相结合，以确保即使在一个或两个采样步骤的低阶模式下也能获得高图像保真度。

开发单位：Stability AI

SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis. SDXL-Turbo is based o* * **vel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), 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