Increase colorspace detection steps from 5 to 15 for clearer color signal

videogen.py

@@ -1225,7 +1225,7 @@ def detect_model_colorspace(pipe, model_name, m_info, args):
     # (128x128 test frame, 5 inference steps), so it works even with low free RAM
     
     print(f"  🔍 Detecting colorspace for {model_name}...")
-    print(f"     (Using minimal resources - 128x128, 5 steps)")
+    print(f"     (Using minimal resources - 128x128, 15 steps)")
     
     try:
         # Use VERY small dimensions and minimal steps to conserve memory
@@ -1245,7 +1245,7 @@ def detect_model_colorspace(pipe, model_name, m_info, args):
                 "height": test_height,
                 "width": test_width,
                 "num_frames": test_frames,
-                "num_inference_steps": 5,  # Very minimal steps
+                "num_inference_steps": 15,  # Sufficient steps for clear color signal
                 "guidance_scale": 3.0,  # Lower guidance to reduce memory
             }