Make Qwen Image 2.1 the production image worker

compose.yaml

@@ -572,7 +572,7 @@ services:
       ALLOWED_PROFILES: fast,medium,large,ultra,uncensored
       IMAGE_WORKER: image
       RESTORE_WORKER: restore
-      QWEN_IMAGE_TEST_WORKER: qwen-image-2.1-test
+      FLUX_STANDBY_WORKER: flux-standby
       TTS_WORKER: qwen3
       MUSIC_WORKER: acestep
       YUE2_WORKER: yue2
@@ -631,7 +631,8 @@ services:
       IMAGE_DIR: /data/images
       IMAGE_WORKER_URL: http://image-worker:8086
       IMAGE_WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
-      IMAGE_MODEL_NAME: FLUX.2-klein-9B-fp8-beta
+      IMAGE_MODEL_NAME: Qwen-Image-2.1-int8
+      IMAGE_INFERENCE_STEPS: "25"
       CHAT_IMAGE_ALLOW_REMOTE_URLS: "false"
       ENABLE_IMAGE_GENERATION: "true"
       ENABLE_TTS: "true"
@@ -673,6 +674,51 @@ services:
         condition: service_healthy
 
   image-worker:
+    build:
+      context: platform/docker/qwen-image-worker
+      args:
+        COMFYUI_COMMIT: b0f4b7b294ce482a2e071d9d762c133d38c7aa07
+    image: mike-ai/qwen-image-worker:local
+    container_name: mike-ai-image-worker
+    restart: "no"
+    profiles: [image]
+    labels:
+      com.mike-ai.image-worker: image
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["${QWEN_IMAGE_21_GPU:-1}"]
+              capabilities: [gpu]
+    read_only: true
+    tmpfs:
+      - /tmp:size=4g,mode=1777
+      - /opt/ComfyUI/user:size=64m,mode=0755
+      - /opt/ComfyUI/temp:size=4g,mode=1777
+      - /opt/ComfyUI/input:size=512m,mode=0755
+    volumes:
+      - "${QWEN_IMAGE_21_MODEL_DIR:-/data/models/Qwen-Image-2.1-ComfyUI}:/opt/ComfyUI/models:ro"
+      - router-images:/data/images
+    environment:
+      NVIDIA_DRIVER_CAPABILITIES: compute,utility
+      PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
+      WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
+      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: 90
+      start_period: 10s
+
+  # Previous production image model, retained as a stopped rollback target.
+  # It is outside the normal router path and can only be started through the
+  # controller's allowlisted flux-standby endpoint.
+  flux-image-worker:
     build:
       context: platform/docker/image-worker
       args:
@@ -681,11 +727,11 @@ services:
         ACCELERATE_VERSION: ${ACCELERATE_VERSION:-1.14.0}
         HF_HUB_VERSION: ${HF_HUB_VERSION:-1.28.0}
     image: mike-ai/image-worker:local
-    container_name: mike-ai-image-worker
+    container_name: mike-ai-flux-image-worker
     restart: "no"
-    profiles: [image]
+    profiles: [flux-standby]
     labels:
-      com.mike-ai.image-worker: image
+      com.mike-ai.image-worker: flux-standby
     gpus: all
     read_only: true
     tmpfs: ["/tmp:size=1g,mode=1777"]
@@ -709,76 +755,6 @@ services:
       timeout: 3s
       retries: 12
 
-  # Isolated evaluation target. It is created in a stopped state by the
-  # preparation script and can only be started through the controller's
-  # allowlisted, GPU-exclusive test endpoint.
-  qwen-image-21-test:
-    build:
-      context: platform/docker/qwen-image-21-test
-      args:
-        COMFYUI_COMMIT: b0f4b7b294ce482a2e071d9d762c133d38c7aa07
-    image: mike-ai/qwen-image-2.1-test:local
-    container_name: mike-ai-qwen-image-2.1-test
-    restart: "no"
-    profiles: [qwen-image-test]
-    labels:
-      com.mike-ai.image-worker: qwen-image-2.1-test
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ["${QWEN_IMAGE_21_GPU:-1}"]
-              capabilities: [gpu]
-    read_only: true
-    tmpfs:
-      - /tmp:size=4g,mode=1777
-      - /opt/ComfyUI/user:size=64m,mode=0755
-      - /opt/ComfyUI/temp:size=4g,mode=1777
-    volumes:
-      - "${QWEN_IMAGE_21_MODEL_DIR:-/data/models/Qwen-Image-2.1-ComfyUI}:/opt/ComfyUI/models:ro"
-      - "${QWEN_IMAGE_21_OUTPUT_DIR:-/data/qwen-image-2.1-test-output}:/opt/ComfyUI/output"
-    environment:
-      NVIDIA_DRIVER_CAPABILITIES: compute,utility
-      PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
-    command:
-      - python
-      - main.py
-      - --listen
-      - 0.0.0.0
-      - --port
-      - "8188"
-      - --lowvram
-      - --preview-method
-      - none
-    networks: [inference]
-    security_opt: ["no-new-privileges:true"]
-    cap_drop: [ALL]
-    healthcheck:
-      test: [CMD, python, -c, "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8188/system_stats', timeout=2)"]
-      interval: 5s
-      timeout: 3s
-      retries: 60
-      start_period: 10s
-
-  qwen-image-21-test-runner:
-    image: python:3.12-slim
-    profiles: [qwen-image-test]
-    read_only: true
-    tmpfs: ["/tmp:size=32m,mode=1777"]
-    volumes:
-      - ./scripts/qwen-image-21-test.py:/opt/test/run.py:ro
-      - "${QWEN_IMAGE_21_OUTPUT_DIR:-/data/qwen-image-2.1-test-output}:/output"
-    environment:
-      CONTROLLER_URL: http://profile-controller:8090
-      CONTROLLER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
-      COMFY_URL: http://qwen-image-21-test:8188
-      OUTPUT_DIR: /output
-    command: [python, /opt/test/run.py]
-    networks: [control, inference]
-    security_opt: ["no-new-privileges:true"]
-    cap_drop: [ALL]
-
   qwen3-tts:
     image: ${QWEN3_TTS_IMAGE:-ghcr.io/malaiwah/qwen3-tts-server:latest@sha256:b363a01d08b1bbecbfc3ca6f585368fae2cfdc591f9ecca6643738369f9a9d98}
     container_name: mike-ai-qwen3-tts