Add RTX 5080 FLUX hot-swap worker

compose.yaml

@@ -370,6 +370,7 @@ services:
     environment:
       CONTROLLER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
       ALLOWED_PROFILES: fast,medium,large,ultra,experimental
+      IMAGE_WORKER: flux
     networks: [control]
     security_opt: ["no-new-privileges:true"]
     healthcheck:
@@ -405,8 +406,10 @@ services:
       SWITCH_TIMEOUT: "600"
       REQUEST_TIMEOUT: "600"
       IMAGE_DIR: /data/images
+      IMAGE_WORKER_URL: http://flux-worker:8086
+      IMAGE_WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
       CHAT_IMAGE_ALLOW_REMOTE_URLS: "false"
-      ENABLE_IMAGE_GENERATION: "false"
+      ENABLE_IMAGE_GENERATION: "true"
       ENABLE_TTS: "true"
       TTS_WORKER_URL: http://piper:8085
       TTS_MODEL: piper
@@ -435,6 +438,41 @@ services:
       piper:
         condition: service_healthy
 
+  flux-worker:
+    build:
+      context: platform/docker/flux-worker
+      args:
+        DIFFUSERS_VERSION: ${DIFFUSERS_VERSION:-0.40.0}
+        TRANSFORMERS_VERSION: ${TRANSFORMERS_VERSION:-5.15.1}
+        ACCELERATE_VERSION: ${ACCELERATE_VERSION:-1.14.0}
+        HF_HUB_VERSION: ${HF_HUB_VERSION:-1.28.0}
+    image: mike-ai/flux-worker:local
+    container_name: mike-ai-flux-worker
+    restart: "no"
+    profiles: [image]
+    labels:
+      com.mike-ai.image-worker: flux
+    gpus: all
+    read_only: true
+    tmpfs: ["/tmp:size=1g,mode=1777"]
+    volumes:
+      - "${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}:/models/FLUX.2-klein-4B:ro"
+      - router-images:/data/images
+    environment:
+      NVIDIA_VISIBLE_DEVICES: ${IMAGE_GPU_DEVICES:-1}
+      NVIDIA_DRIVER_CAPABILITIES: compute,utility
+      WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
+      FLUX_MODEL_DIR: /models/FLUX.2-klein-4B
+      IMAGE_DIR: /data/images
+    networks: [inference]
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: [ALL]
+    healthcheck:
+      test: [CMD, python, -c, "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8086/health', timeout=2)"]
+      interval: 5s
+      timeout: 3s
+      retries: 12
+
   piper:
     build:
       context: platform/docker/piper