Remove Flux and MusicGen models from orchestrator

ComfyUI now handles Flux image generation directly.
MusicGen is not being used and has been removed.

model-orchestrator/models.yaml

@@ -13,28 +13,6 @@ models:
     endpoint: /v1/chat/completions
     description: "Qwen 2.5 7B Instruct - Fast text generation, no authentication required"
 
-  # Image Generation Models
-  flux-schnell:
-    type: image
-    framework: openedai-images
-    service_script: models/flux/server.py
-    port: 8002
-    vram_gb: 14
-    startup_time_seconds: 60
-    endpoint: /v1/images/generations
-    description: "Flux.1 Schnell - Fast high-quality image generation (4-5 sec/image)"
-
-  # Music Generation Models
-  musicgen-medium:
-    type: audio
-    framework: audiocraft
-    service_script: models/musicgen/server.py
-    port: 8003
-    vram_gb: 11
-    startup_time_seconds: 45
-    endpoint: /v1/audio/generations
-    description: "MusicGen Medium - Text-to-music generation (60-90 sec for 30s audio)"
-
 # Example: Add more models easily by uncommenting and customizing below
 
 # Future Text Models: