git clone https://github.com/CompVis/stable-diffusion.git- 進(jìn)入stable-diffusion目錄
- 在這里注冊(cè)一個(gè)賬號(hào):?Hugging Face – The AI community building the future.?并生成個(gè)token
- 安裝CUDA?NVIDIA 安裝 CUDA_nvidia cuda_長(zhǎng)滿頭發(fā)的程序猿的博客-CSDN博客
pip install torch -f https://download.pytorch.org/whl/torch_stable.htmlpip install -e git+ https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers-
conda install torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia?選擇合適的pytorch-cuda版本 pip install transformers==4.25.1 diffusers invisible-watermarkpip install -e .-
huggingface-cli login?輸入生成的token
from torch import autocast
from diffusers import StableDiffusionPipeline
import torch
if __name__ == '__main__':
# https://github.com/CompVis/stable-diffusion/issues/69#issuecomment-1260722801
torch.backends.cudnn.benchmark = True
torch.backends.cudnn.enabled = True
pipe = StableDiffusionPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
torch_dtype=torch.float16,
use_auth_token=True,
safety_checker=None,
requires_safety_checker=False
).to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
with autocast("cuda"):
result = pipe(prompt, height=256, width=256)
image = result[0][0]
image.save("test.png")
文章來(lái)源地址http://www.zghlxwxcb.cn/news/detail-541408.html
文章來(lái)源：http://www.zghlxwxcb.cn/news/detail-541408.html
到了這里，關(guān)于stable-diffusion AI 繪畫(huà)的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
![[AI繪圖教程]stable-diffusion webui加載模型與插件. 實(shí)戰(zhàn)AI繪畫(huà)](https://imgs.yssmx.com/Uploads/2024/01/407805-1.png)
