mklink d:\diffusion\models\Stable-diffusion\Official-SDXL\sd_xl_base_1.0.safetensors D:\diffusion\stabilityai_stable-diffusion-xl-base-1.0\sd_xl_base_1.0.safetensors
Command line builder to install PyTorch
For Windows:
pip3 install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cu117
Removing the existing packages:
pip uninstall charset-normalizer idna mpmath networkx numpy pillow requests sympy torch torchaudio torchvision typing-extensions functorch clean-fid
Here is basic code to generate some images:
from diffusers import StableDiffusionXLPipeline, UniPCMultistepScheduler import torch pipe = StableDiffusionXLPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16") pipe.to("cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config) image = pipe(prompt=prompt, num_inference_steps=20).images[0]