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) (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: <a rel="ugc" href="https://huggingface.co/stabilityai/sdxl-turbo/tree/main">Stability AI</a>

SDXL Turbo

sdxlTurbo_sdxlTurboPruned.safetensors

SDXL Turbo Pruned

Full Version

Model Sources: <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0.safetensors">https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0.safetensors</a>

Stable Diffusion XL_Turbo 1.0

sd_xl_turbo_1.0_fp16.safetensors

fp16

SDXL-Turbo

From Stability.ai: currently being released under a non-commercial research license that permits personal, non-commercial use.

Files with SHA256: e869ac7d6942cb327d68d5ed83a40447aadf20e0c3358d98b2cc9e270db0da26