Add dual-GPU FLUX 9B image pipeline

compose.yaml

@@ -571,6 +571,7 @@ services:
       CONTROLLER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
       ALLOWED_PROFILES: fast,medium,beta1,large,ultra,uncensored
       IMAGE_WORKER: image
+      TTS_WORKER: qwen3
     networks: [control]
     security_opt: ["no-new-privileges:true"]
     healthcheck:
@@ -615,14 +616,13 @@ services:
       IMAGE_DIR: /data/images
       IMAGE_WORKER_URL: http://image-worker:8086
       IMAGE_WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
-      IMAGE_MODEL_NAME: FLUX.2-klein-4B
+      IMAGE_MODEL_NAME: FLUX.2-klein-9B-fp8-beta
       CHAT_IMAGE_ALLOW_REMOTE_URLS: "false"
       ENABLE_IMAGE_GENERATION: "true"
       ENABLE_TTS: "true"
-      # Stable OpenAI compatibility names remain piper/alloy because an
-      # existing Open WebUI database persists those values. The gateway maps
-      # alloy to XTTS speaker Annmarie Nele and automatically falls back to
-      # Piper if XTTS is unavailable, busy or returns an error.
+      # Stable OpenAI compatibility names remain piper/alloy for existing
+      # clients. The gateway maps them to Qwen3-TTS and falls back to Piper
+      # while Qwen3-TTS is unavailable, busy or paused for image generation.
       TTS_WORKER_URL: http://tts-gateway:8085
       TTS_MODEL: piper
       TTS_VOICES: alloy
@@ -674,13 +674,15 @@ services:
     read_only: true
     tmpfs: ["/tmp:size=1g,mode=1777"]
     volumes:
-      - "${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}:/models/FLUX.2-klein-4B:ro"
+      - "${FLUX_COMPONENT_DIR:-/data/models/FLUX.2-klein-9B-components}:/models/components:ro"
+      - "${FLUX_TRANSFORMER_DIR:-/data/models/FLUX.2-klein-9B-fp8}:/models/fp8:ro"
       - router-images:/data/images
     environment:
-      NVIDIA_VISIBLE_DEVICES: ${IMAGE_GPU_DEVICES:-1}
+      NVIDIA_VISIBLE_DEVICES: all
       NVIDIA_DRIVER_CAPABILITIES: compute,utility
       WORKER_TOKEN: "${CONTROLLER_TOKEN:?CONTROLLER_TOKEN is required}"
-      FLUX_MODEL_DIR: /models/FLUX.2-klein-4B
+      FLUX_COMPONENT_DIR: /models/components
+      FLUX_TRANSFORMER_FILE: /models/fp8/flux-2-klein-9b-fp8.safetensors
       IMAGE_DIR: /data/images
     networks: [inference]
     security_opt: ["no-new-privileges:true"]
@@ -726,6 +728,8 @@ services:
     image: ${QWEN3_TTS_IMAGE:-ghcr.io/malaiwah/qwen3-tts-server:latest@sha256:b363a01d08b1bbecbfc3ca6f585368fae2cfdc591f9ecca6643738369f9a9d98}
     container_name: mike-ai-qwen3-tts
     restart: unless-stopped
+    labels:
+      com.mike-ai.tts-worker: qwen3
     deploy:
       resources:
         reservations: