Add MMAudioSampler to experimental audio model loaders in __init__.py so it stays in sync with the Model and FeatureUtils Loaders. I suspect this is because it is querying the cuda device directly. This would give the wrong answer half the time depending on how the other loaders were ran via the sequencing logic.

This will sync up those cuda device queries with the patched version from MultiGPU.
2024-12-26 14:59:16 -06:00
parent 94cf7d9779
commit dead358227
1 changed files with 1 additions and 1 deletions
@@ -43,7 +43,7 @@ TARGET_NODE_NAMES = {
    "LoadFluxControlNet",                                                                                                                   # x-flux-comfyui - https://github.com/XLabs-AI/x-flux-comfyui
    "Florence2ModelLoader", "DownloadAndLoadFlorence2Model",                                                                                # ComfyUI-Florence2 - https://github.com/kijai/ComfyUI-Florence2
    "LTXVLoader",                                                                                                                           # ComfyUI-LTXVideo - https://github.com/Lightricks/ComfyUI-LTXVideo
-    "MMAudioFeatureUtilsLoader", "MMAudioModelLoader",                                                                                      # ComfyUI-MMAudio - https://github.com/kijai/ComfyUI-MMAudio --EXPERIMENTAL--
+    "MMAudioFeatureUtilsLoader", "MMAudioModelLoader", "MMAudioSampler",                                                                    # ComfyUI-MMAudio - https://github.com/kijai/ComfyUI-MMAudio --EXPERIMENTAL--
 }

 NODE_CLASS_MAPPINGS = {}