feat: add ComfyUI, rebalance GPU allocation

GPU rebalance (4× V100 32GB on worker-1):
- reasoning: 2 GPU (unchanged, PP=2 for Qwen3-32B)
- ornith: 2→1 GPU (scale to 1 replica, ornith:35b only)
- comfyui: 0→1 GPU (new)
- embeddings/reranker: 0 GPU (CPU, unchanged)

qwen2.5:3b-instruct moved to CPU on talos-cp-2 (144GB RAM).
Separate Ollama deployment + 5Gi PVC, pulls model on first start.

Gateway config updated in homelab-frontend (separate commit).

Co-authored-by: poimen <[email protected]>

k8s/apps/comfyui/deployment.yaml

@@ -0,0 +1,80 @@
+# 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:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: comfyui
+  template:
+    metadata:
+      labels:
+        app: comfyui
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: worker-1
+      runtimeClassName: nvidia
+      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"
+            - name: COMFYUI_FLAGS
+              value: "--listen 0.0.0.0 --port 8188"
+          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: 60
+            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

k8s/apps/comfyui/ingress.yaml

@@ -0,0 +1,25 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: comfyui
+  namespace: comfyui
+  annotations:
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
+    nginx.ingress.kubernetes.io/proxy-body-size: "0"
+    # WebSocket support for ComfyUI's live preview
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    nginx.ingress.kubernetes.io/proxy-set-headers: "Upgrade"
+spec:
+  ingressClassName: nginx
+  rules:
+    - host: comfy.riotpiao.com
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: comfyui
+                port:
+                  number: 80

k8s/apps/comfyui/kustomization.yaml

@@ -0,0 +1,7 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - deployment.yaml
+  - service.yaml
+  - ingress.yaml

k8s/apps/comfyui/service.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: comfyui
+  namespace: comfyui
+  labels:
+    app: comfyui
+spec:
+  selector:
+    app: comfyui
+  ports:
+    - port: 80
+      targetPort: 8188
+      protocol: TCP