Container Service for Kubernetes:Deploy a Stable Diffusion application in an ACK Serverless cluster

On the Deployments page, click Create from Image.

On the Basic Information tab, specify a name, such as stable-diffusion, and then click Next.

On the Advanced page, click Create.

If the following page is returned, the application is created. You can click View Details to view information about the application on the Pods, Access Method, Events, Pod Scaling, History Versions, Logs, or Triggers tab.

After the status of the pod changes to Running, the Stable Diffusion application is deployed.

A kubectl client is connected to the cluster. For more information, see Obtain the kubeconfig file of a cluster and use kubectl to connect to the cluster.

Create a YAML file named stable-diffusion.yaml and copy the following content to the file.

In the following sample code, image is the public network address. To pull the image over an internal network, replace the image address based on the cluster region.

• China (Beijing): registry-vpc.cn-beijing.aliyuncs.com/yunqi-lab/stable-diffusion:v1.2.0

• China (Shanghai): registry-vpc.cn-shanghai.aliyuncs.com/yunqi-lab/stable-diffusion:v1.2.0

• China (Hangzhou): registry-vpc.cn-hangzhou.aliyuncs.com/yunqi-lab/stable-diffusion:v1.2.0

• China (Shenzhen): registry-vpc.cn-shenzhen.aliyuncs.com/yunqi-lab/stable-diffusion:v1.2.0

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: stable-diffusion
  name: stable-diffusion
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: stable-diffusion
  template:
    metadata:
      labels:
        app: stable-diffusion
    spec:
      containers:
      - args:
        - --listen
        - --skip-torch-cuda-test
        - --no-half
        command:
        - python3
        - launch.py
        image: yunqi-registry.cn-shanghai.cr.aliyuncs.com/lab/stable-diffusion:v1.2.0
        imagePullPolicy: IfNotPresent
        name: stable-diffusion
        ports:
        - containerPort: 7860
          protocol: TCP
        readinessProbe:
          tcpSocket:
            port: 7860
        resources:
          limits:
            cpu: "8"
            memory: 16Gi
            ephemeral-storage: 50Gi
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    service.beta.kubernetes.io/alibaba-cloud-loadbalancer-address-type: internet
    service.beta.kubernetes.io/alibaba-cloud-loadbalancer-instance-charge-type: PayByCLCU
  name: stable-diffusion-svc
  namespace: default
spec:
  externalTrafficPolicy: Local
  ports:
  - port: 7860
    protocol: TCP
    targetPort: 7860
  selector:
    app: stable-diffusion
  type: LoadBalancer

Run the following command to deploy the Stable Diffusion application:

kubectl apply -f stable-diffusion.yaml 

Run the following command to query the status of the application:

kubectl get deployment stable-diffusion

Expected output:

NAME              READY   UP-TO-DATE   AVAILABLE    AGE
stable-diffusion   1/1     1            1           103m