Add RTX 5080 FLUX hot-swap worker

install.sh

@@ -226,6 +226,8 @@ LARGE_TENSOR_SPLIT=${LARGE_TENSOR_SPLIT:-86,14}
 ULTRA_GPU_DEVICES=${TEXT_GPU_DEVICES:-0}${SECONDARY_GPU_DEVICES:+,$SECONDARY_GPU_DEVICES}
 ULTRA_TENSOR_SPLIT=${ULTRA_TENSOR_SPLIT:-80,20}
 EXPERIMENTAL_GPU_DEVICES=${TEXT_GPU_DEVICES:-0}
+IMAGE_GPU_DEVICES=${IMAGE_GPU_DEVICES:-${TEXT_GPU_DEVICES:-0}}
+FLUX_MODEL_DIR=${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}
 LLAMA_THREADS=${LLAMA_THREADS:-6}
 LLAMA_THREADS_BATCH=${LLAMA_THREADS_BATCH:-6}
 EOF
@@ -326,12 +328,23 @@ build_and_start() {
   cd "$STACK_DIR"
   docker build --progress=plain --build-arg LLAMA_CPP_COMMIT="$commit" \
     -f platform/docker/llama-cpp/Dockerfile -t mike-ai/llama.cpp:local .
+  docker compose --env-file "$SECRETS_DIR/stack.env" --profile image build flux-worker
+  if [[ ! -s ${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}/model_index.json ]]; then
+    log "FLUX.2 Klein Distilled laden"
+    install -d -m 0755 "${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}"
+    docker run --rm --entrypoint python \
+      -v "${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}:/download" \
+      mike-ai/flux-worker:local -c \
+      "from huggingface_hub import snapshot_download; snapshot_download('black-forest-labs/FLUX.2-klein-4B', revision='303481f0390afb112393f9d77e8f0be72fcefeb7', local_dir='/download')"
+    chmod -R a-w "${FLUX_MODEL_DIR:-/data/models/FLUX.2-klein-4B}"
+  fi
   # Creates the shared internal tools network before Open WebUI is created.
   # Web search always starts; HA/ARR/Unraid only start when their root-only
   # secret files and required local artifacts are present.
   "$STACK_DIR/platform/mcp/install-tools.sh"
   docker compose --env-file "$SECRETS_DIR/stack.env" --profile inference create \
     llama-fast llama-medium llama-large llama-ultra llama-experimental
+  docker compose --env-file "$SECRETS_DIR/stack.env" --profile image create flux-worker
   docker compose --env-file "$SECRETS_DIR/stack.env" up -d --build \
     profile-controller router open-webui