How to use openskyml/sd-turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("openskyml/sd-turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "turbo" image = pipe(prompt).images[0]
Fast generate images with SD-turbo!
Base model
