Make Qwen Image 2.1 the production image worker

platform/docker/profile-controller/profile_controller.py

@@ -27,8 +27,8 @@ LABEL_KEY = "com.mike-ai.llama-profile"
 IMAGE_LABEL_KEY = "com.mike-ai.image-worker"
 IMAGE_WORKER = os.environ.get("IMAGE_WORKER", "image")
 RESTORE_WORKER = os.environ.get("RESTORE_WORKER", "restore")
-QWEN_IMAGE_TEST_WORKER = os.environ.get(
-    "QWEN_IMAGE_TEST_WORKER", "qwen-image-2.1-test").strip()
+FLUX_STANDBY_WORKER = os.environ.get(
+    "FLUX_STANDBY_WORKER", "flux-standby").strip()
 TTS_LABEL_KEY = "com.mike-ai.tts-worker"
 TTS_WORKER = os.environ.get("TTS_WORKER", "qwen3")
 MUSIC_LABEL_KEY = "com.mike-ai.music-worker"
@@ -103,8 +103,8 @@ def image_container(kind: str = IMAGE_WORKER) -> dict:
 def image_containers() -> list[dict]:
     """All allowlisted GPU workers that must never overlap an LLM."""
     allowed = {IMAGE_WORKER, RESTORE_WORKER}
-    if QWEN_IMAGE_TEST_WORKER:
-        allowed.add(QWEN_IMAGE_TEST_WORKER)
+    if FLUX_STANDBY_WORKER:
+        allowed.add(FLUX_STANDBY_WORKER)
     return [item for item in labelled_containers(IMAGE_LABEL_KEY)
             if item.get("Labels", {}).get(IMAGE_LABEL_KEY) in allowed]
 
@@ -363,7 +363,7 @@ def stop_inference() -> dict:
 
 
 def set_image_worker(running: bool, kind: str = IMAGE_WORKER) -> dict:
-    if kind not in {IMAGE_WORKER, RESTORE_WORKER, QWEN_IMAGE_TEST_WORKER}:
+    if kind not in {IMAGE_WORKER, RESTORE_WORKER, FLUX_STANDBY_WORKER}:
         raise ValueError("worker is not allowlisted")
     with LOCK:
         item = image_container(kind)
@@ -371,8 +371,8 @@ def set_image_worker(running: bool, kind: str = IMAGE_WORKER) -> dict:
             # The image worker may never overlap a llama profile on the 5080.
             for profile_item in containers().values():
                 stop_container(profile_item)
-            # The 9B beta text encoder temporarily borrows the RTX 3060 from
-            # Qwen3-TTS. TTS is unavailable during this exclusive GPU phase.
+            # Image workers are GPU-exclusive. The FLUX standby also borrows
+            # the RTX 3060, while Qwen Image runs only on the RTX 5080.
             stop_container(tts_container(), timeout=30)
             stop_music_if_configured()
             stop_yue2_if_configured()
@@ -801,8 +801,8 @@ class Handler(BaseHTTPRequestHandler):
             "/workers/image/stop": (IMAGE_WORKER, False),
             "/workers/restore/start": (RESTORE_WORKER, True),
             "/workers/restore/stop": (RESTORE_WORKER, False),
-            "/workers/qwen-image-test/start": (QWEN_IMAGE_TEST_WORKER, True),
-            "/workers/qwen-image-test/stop": (QWEN_IMAGE_TEST_WORKER, False),
+            "/workers/flux-standby/start": (FLUX_STANDBY_WORKER, True),
+            "/workers/flux-standby/stop": (FLUX_STANDBY_WORKER, False),
         }
         if self.path in worker_paths:
             try: