ARM架构推理Stable Diffusiond

 代码仓库：

https://github.com/siutin/stable-diffusion-webui-docker.git

Docker容器地址：

https://hub.docker.com/r/siutin/stable-diffusion-webui-docker/tags

git clone https://github.com/siutin/stable-diffusion-webui-docker.git
cd stable-diffusion-webui-docker

 准备主机中的目录映射：

创建目录

mkdir -p /MY-DATA-DIR && cd /MY-DATA-DIR
mkdir models outputs
sudo chown 10000:$UID -R models outputs
sudo chmod 775 -R models outputs

使用 CUDA 运行

# With the latest CUDA version
docker run -it –name sdw –gpus all –network host
  -v $(pwd)/models:/app/stable-diffusion-webui/models
  -v $(pwd)/outputs:/app/stable-diffusion-webui/outputs
  –rm siutin/stable-diffusion-webui-docker:latest-cuda
  bash webui.sh –share

# With specific CUDA version
docker run -it –name sdw –gpus all –network host
  -v $(pwd)/models:/app/stable-diffusion-webui/models
  -v $(pwd)/outputs:/app/stable-diffusion-webui/outputs
  –rm siutin/stable-diffusion-webui-docker:latest-cuda-12.6.2
  bash webui.sh –share

 仅使用 CPU 运行

docker run -it –name sdw –network host
  -v $(pwd)/models:/app/stable-diffusion-webui/models
  -v $(pwd)/outputs:/app/stable-diffusion-webui/outputs
  –rm siutin/stable-diffusion-webui-docker:latest-cpu
  bash webui.sh –skip-torch-cuda-test –use-cpu all –share

构建自定义镜像

# Nvidia CUDA image
nvidia-docker buildx build -f Dockerfile.cuda
                           –platform linux/amd64
                           –build-arg BUILD_DATE=$(date -u +’%Y-%m-%dT%H:%M:%SZ’)
                           –build-arg BUILD_VERSION=custom-cuda
                           -t siutin/stable-diffusion-webui-docker:custom-cuda .

# Nvidia CUDA image with specific version
nvidia-docker buildx build -f Dockerfile.cuda
                           –platform linux/amd64
                           –build-arg BUILD_DATE=$(date -u +’%Y-%m-%dT%H:%M:%SZ’)
                           –build-arg BUILD_VERSION=custom-cuda
                           –build-arg CUDA_VERSION=12.5.1
                           -t siutin/stable-diffusion-webui-docker:custom-cuda-12.5 .

# CPU only image
docker buildx build -f Dockerfile.cpu
                           –platform linux/arm64
                           –build-arg BUILD_DATE=$(date -u +’%Y-%m-%dT%H:%M:%SZ’)
                           –build-arg BUILD_VERSION=custom-cpu
                           -t siutin/stable-diffusion-webui-docker:custom-cpu .

docker run -it –name sdw –gpus all –network host

  -v /home/ai/Project/SD模型/sd-webui

/models:/app/stable-diffusion-webui/models

  -v /home/ai/Project/SD模型/sd-webui

/outputs:/app/stable-diffusion-webui/outputs

  –rm siutin/stable-diffusion-webui-docker :cpu-v1.10.1-2025-02-10

  bash webui.sh –share

Ubuntu 20.04 focal 版本（适合 ARM 64）

sudo tee /etc/apt/sources.list > /dev/null # 默认注释了源码镜像以提高 apt update 速度，如有需要可自行取消注释
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-updates main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-updates main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-backports main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-backports main restricted universe multiverse

# 安全更新源
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-security main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ focal-security main restricted universe multiverse

# Docker 镜像源（arm64）
deb [arch=arm64] https://mirrors.aliyun.com/docker-ce/linux/ubuntu focal stable
# deb-src [arch=arm64] https://mirrors.aliyun.com/docker-ce/linux/ubuntu focal stable
EOF
 

Ubuntu 22.04 jammy 版本（适合 ARM 64）

sudo tee /etc/apt/sources.list > /dev/null # 默认注释了源码镜像以提高 apt update 速度，如有需要可自行取消注释
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-updates main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-updates main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-backports main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-backports main restricted universe multiverse

# 安全更新源
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-security main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ jammy-security main restricted universe multiverse

# Docker 镜像源（arm64）
deb [arch=arm64] https://mirrors.aliyun.com/docker-ce/linux/ubuntu jammy stable
# deb-src [arch=arm64] https://mirrors.aliyun.com/docker-ce/linux/ubuntu jammy stable
EOF
 

构建镜像

docker buildx build -f Dockerfile.cuda   –platform linux/arm64   –build-arg BUILD_DATE=$(date -u +’%Y-%m-%dT%H:%M:%SZ’)   –build-arg BUILD_VERSION=custom-cuda-12.4   –build-arg CUDA_VERSION=12.4.0   -t siutin/stable-diffusion-webui-docker:custom-cuda-12.4 .
 

文章来源于互联网:ARM架构推理Stable Diffusiond