Merge c7843f888f into 0fd10ffa09

README.md

@@ -240,7 +240,7 @@ These have less hardware support than the builds above but they work on windows.
 
 RDNA 3 (RX 7000 series):
 
-```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/```
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/```
 
 RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
 

comfy_api/latest/_input_impl/video_types.py

@@ -374,7 +374,7 @@ class VideoFromComponents(VideoInput):
             if audio_stream and self.__components.audio:
                 waveform = self.__components.audio['waveform']
                 waveform = waveform[:, :, :math.ceil((audio_sample_rate / frame_rate) * self.__components.images.shape[0])]
-                frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
+                frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().cpu().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
                 frame.sample_rate = audio_sample_rate
                 frame.pts = 0
                 output.mux(audio_stream.encode(frame))

comfy_api/latest/_io.py

@@ -1125,6 +1125,25 @@ class ImageCompare(ComfyTypeI):
       def as_dict(self):
           return super().as_dict()
 
+@comfytype(io_type="BOUNDINGBOX")
+class BoundingBox(ComfyTypeIO):
+    Type = dict
+
+    class Input(WidgetInput):
+        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
+                     socketless: bool=True, default: dict=None, component: str=None):
+            super().__init__(id, display_name, optional, tooltip, None, default, socketless)
+            self.component = component
+            if default is None:
+                self.default = {"x": 0, "y": 0, "width": 512, "height": 512}
+
+        def as_dict(self):
+            d = super().as_dict()
+            if self.component:
+                d["component"] = self.component
+            return d
+
+
 DYNAMIC_INPUT_LOOKUP: dict[str, Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]] = {}
 def register_dynamic_input_func(io_type: str, func: Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]):
     DYNAMIC_INPUT_LOOKUP[io_type] = func
@@ -2046,4 +2065,5 @@ __all__ = [
     "ImageCompare",
     "PriceBadgeDepends",
     "PriceBadge",
+    "BoundingBox",
 ]

comfy_extras/nodes_images.py

@@ -26,16 +26,18 @@ class ImageCrop(IO.ComfyNode):
             category="image/transform",
             inputs=[
                 IO.Image.Input("image"),
-                IO.Int.Input("width", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
-                IO.Int.Input("height", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
-                IO.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1),
-                IO.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1),
+                IO.BoundingBox.Input("crop_region", component="ImageCrop"),
             ],
             outputs=[IO.Image.Output()],
         )
 
     @classmethod
-    def execute(cls, image, width, height, x, y) -> IO.NodeOutput:
+    def execute(cls, image, crop_region) -> IO.NodeOutput:
+        x = crop_region.get("x", 0)
+        y = crop_region.get("y", 0)
+        width = crop_region.get("width", 512)
+        height = crop_region.get("height", 512)
+
         x = min(x, image.shape[2] - 1)
         y = min(y, image.shape[1] - 1)
         to_x = width + x
@@ -46,6 +48,27 @@ class ImageCrop(IO.ComfyNode):
     crop = execute  # TODO: remove
 
 
+class IntToBoundingBox(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="IntToBoundingBox",
+            display_name="INT to Bounding Box",
+            category="utils",
+            inputs=[
+                IO.Int.Input("x", default=0, min=0, max=MAX_RESOLUTION),
+                IO.Int.Input("y", default=0, min=0, max=MAX_RESOLUTION),
+                IO.Int.Input("width", default=512, min=1, max=MAX_RESOLUTION),
+                IO.Int.Input("height", default=512, min=1, max=MAX_RESOLUTION),
+            ],
+            outputs=[IO.BoundingBox.Output(display_name="BOUNDINGBOX")],
+        )
+
+    @classmethod
+    def execute(cls, x, y, width, height) -> IO.NodeOutput:
+        return IO.NodeOutput({"x": x, "y": y, "width": width, "height": height})
+
+
 class RepeatImageBatch(IO.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -628,6 +651,7 @@ class ImagesExtension(ComfyExtension):
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
         return [
             ImageCrop,
+            IntToBoundingBox,
             RepeatImageBatch,
             ImageFromBatch,
             ImageAddNoise,