# ComfyUI — GPU-accelerated image generation on worker-1.
# Uses 1x V100 32GB (sm70). Freed by scaling ornith 2→1.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: comfyui
  namespace: comfyui
  labels:
    app: comfyui
spec:
  # Retired on purpose. This Deployment held the 4th V100 on worker-1 while
  # serving nothing: its oauth2-proxy roll-out has been stuck for 42h and
  # failing 11621 times, because the Secret comfyui/comfyui-oauth2-proxy carries
  # only 1 key while the pod requests client-id, client-secret and
  # cookie-secret. Every request was therefore refused, so the card sat at 0%
  # utilisation and blocked a GPU that llm-serving can use.
  #
  # Scaling to 0 is the whole change. The Deployment, the Service, the Ingress
  # and the 50Gi comfyui-models PVC all stay, so nothing is lost and no data is
  # touched. To bring it back: set replicas to 1 here, then fix the Secret to
  # carry all three keys, otherwise the same stuck roll-out returns.
  replicas: 0
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: comfyui
  template:
    metadata:
      labels:
        app: comfyui
    spec:
      nodeSelector:
        kubernetes.io/hostname: worker-1
      runtimeClassName: nvidia
      # k8s Service named 'comfyui' injects COMFYUI_PORT=tcp://... into pod env,
      # which clobbers ai-dock's own COMFYUI_PORT variable (expects a port number).
      # Disable service link injection to avoid the collision.
      enableServiceLinks: false
      containers:
        - name: comfyui
          image: ghcr.io/ai-dock/comfyui:v2-cuda-12.1.1-base-22.04
          ports:
            - containerPort: 8188
              protocol: TCP
          env:
            - name: NVIDIA_VISIBLE_DEVICES
              value: "all"
          resources:
            requests:
              cpu: "4"
              memory: 8Gi
              nvidia.com/gpu: "1"
            limits:
              cpu: "8"
              memory: 16Gi
              nvidia.com/gpu: "1"
          volumeMounts:
            - mountPath: /workspace/ComfyUI/models
              name: models
            - mountPath: /workspace/ComfyUI/output
              name: output
          readinessProbe:
            httpGet:
              path: /
              port: 8188
            periodSeconds: 10
            initialDelaySeconds: 30
          startupProbe:
            httpGet:
              path: /
              port: 8188
            failureThreshold: 120
            periodSeconds: 10
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: comfyui-models
        - name: output
          emptyDir: {}
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: comfyui-models
  namespace: comfyui
spec:
  accessModes:
    - ReadWriteOnce
  storageClassName: longhorn
  resources:
    requests:
      storage: 50Gi