苹果M1芯片上运行Stable Diffusion(文字作画)

1 源码下载

git clone -b apple-silicon-mps-support https://github.com/bfirsh/stable-diffusion.git
cd stable-diffusion

2 修改gitee国内源(如果可以稳定访问github就不需要)

numpy==1.23.1
--pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu

albumentations==0.4.6
diffusers
opencv-python==4.6.0.66
pudb==2019.2
invisible-watermark
imageio==2.9.0
imageio-ffmpeg==0.4.2
pytorch-lightning==1.4.2
omegaconf==2.1.1
test-tube>=0.7.5
streamlit>=0.73.1
einops==0.3.0
torch-fidelity==0.3.0
transformers==4.19.2
torchmetrics==0.6.0
kornia==0.6
-e git+https://gitee.com/rexiyz/taming-transformers.git@master#egg=taming-transformers
-e git+https://gitee.com/arcsion/CLIP.git@main#egg=clip

3 安装依赖

pip install -r requirements.txt

3.1 如果onnx报错，安装protobuf

brew install Cmake protobuf rust
brew link --overwrite protobuf

3.2 如果grpcio报错(链接)

brew install openssl

CFLAGS="-I/opt/homebrew/opt/openssl/include" LDFLAGS="-L/opt/homebrew/opt/openssl/lib" GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1 GRPC_PYTHON_BUILD_SYSTEM_ZLIB=1 pip install grpcio

4 下载模型文件(链接)

https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt

放到源码目录下的

models/ldm/stable-diffusion-v1/model.ckpt

5 执行图片生成

 python scripts/txt2img.py \                                                     
  --prompt "a red juicy apple floating in outer space, like a planet" \
  --n_samples 1 --n_iter 1 --plms

会自定下载模型文件，有人说下载慢，时间段不同，但是我下载很快没有啥问题

5.1 如果报错As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1`

执行

export PYTORCH_ENABLE_MPS_FALLBACK=1

5.2 查看效果