Merge 14e7ca7dc8 into f3ea976cba

* Batch broadcasting in JoinImageWithAlpha node

comfy/cli_args.py

@@ -91,6 +91,7 @@ parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE"
 
 parser.add_argument("--oneapi-device-selector", type=str, default=None, metavar="SELECTOR_STRING", help="Sets the oneAPI device(s) this instance will use.")
 parser.add_argument("--supports-fp8-compute", action="store_true", help="ComfyUI will act like if the device supports fp8 compute.")
+parser.add_argument("--enable-triton-backend", action="store_true", help="ComfyUI will enable the use of Triton backend in comfy-kitchen. Is disabled at launch by default.")
 
 class LatentPreviewMethod(enum.Enum):
     NoPreviews = "none"

comfy/quant_ops.py

@@ -1,6 +1,8 @@
 import torch
 import logging
 
+from comfy.cli_args import args
+
 try:
     import comfy_kitchen as ck
     from comfy_kitchen.tensor import (
@@ -21,7 +23,15 @@ try:
             ck.registry.disable("cuda")
             logging.warning("WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.")
 
-    ck.registry.disable("triton")
+    if args.enable_triton_backend:
+        try:
+            import triton
+            logging.info("Found triton %s. Enabling comfy-kitchen triton backend.", triton.__version__)
+        except ImportError as e:
+            logging.error(f"Failed to import triton, Error: {e}, the comfy-kitchen triton backend will not be available.")
+            ck.registry.disable("triton")
+    else:
+        ck.registry.disable("triton")
     for k, v in ck.list_backends().items():
         logging.info(f"Found comfy_kitchen backend {k}: {v}")
 except ImportError as e:

comfy_extras/nodes_compositing.py

@@ -202,14 +202,11 @@ class JoinImageWithAlpha(io.ComfyNode):
 
     @classmethod
     def execute(cls, image: torch.Tensor, alpha: torch.Tensor) -> io.NodeOutput:
-        batch_size = min(len(image), len(alpha))
-        out_images = []
-
+        batch_size = max(len(image), len(alpha))
         alpha = 1.0 - resize_mask(alpha, image.shape[1:])
-        for i in range(batch_size):
-           out_images.append(torch.cat((image[i][:,:,:3], alpha[i].unsqueeze(2)), dim=2))
-
-        return io.NodeOutput(torch.stack(out_images))
+        alpha = comfy.utils.repeat_to_batch_size(alpha, batch_size)
+        image = comfy.utils.repeat_to_batch_size(image, batch_size)
+        return io.NodeOutput(torch.cat((image[..., :3], alpha.unsqueeze(-1)), dim=-1))
 
 
 class CompositingExtension(ComfyExtension):

comfy_extras/nodes_post_processing.py

@@ -666,12 +666,13 @@ class ColorTransfer(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="ColorTransfer",
+            display_name="Color Transfer",
             category="image/postprocessing",
             description="Match the colors of one image to another using various algorithms.",
             search_aliases=["color match", "color grading", "color correction", "match colors", "color transform", "mkl", "reinhard", "histogram"],
             inputs=[
                 io.Image.Input("image_target", tooltip="Image(s) to apply the color transform to."),
-                io.Image.Input("image_ref", optional=True, tooltip="Reference image(s) to match colors to. If not provided, processing is skipped"),
+                io.Image.Input("image_ref", tooltip="Reference image(s) to match colors to."),
                 io.Combo.Input("method", options=['reinhard_lab', 'mkl_lab', 'histogram'],),
                 io.DynamicCombo.Input("source_stats",
                     tooltip="per_frame: each frame matched to image_ref individually. uniform: pool stats across all source frames as baseline, match to image_ref. target_frame: use one chosen frame as the baseline for the transform to image_ref, applied uniformly to all frames (preserves relative differences)",

comfy_extras/nodes_primitive.py

@@ -49,7 +49,7 @@ class Int(io.ComfyNode):
             display_name="Int",
             category="utils/primitive",
             inputs=[
-                io.Int.Input("value", min=-sys.maxsize, max=sys.maxsize, control_after_generate=True),
+                io.Int.Input("value", min=-sys.maxsize, max=sys.maxsize, control_after_generate=io.ControlAfterGenerate.fixed),
             ],
             outputs=[io.Int.Output()],
         )

comfy_extras/nodes_sdpose.py

@@ -252,6 +252,10 @@ class KeypointDraw:
 
                 Y = [keypoints[idx1][0], keypoints[idx2][0]]
                 X = [keypoints[idx1][1], keypoints[idx2][1]]
+
+                if math.isnan(X[0]) or math.isnan(X[1]) or math.isnan(Y[0]) or math.isnan(Y[1]):
+                    continue
+
                 mX, mY = (X[0] + X[1]) / 2, (Y[0] + Y[1]) / 2
                 length = math.sqrt((X[0] - X[1]) ** 2 + (Y[0] - Y[1]) ** 2)
 
@@ -269,6 +273,8 @@ class KeypointDraw:
             for i in range(18):
                 if scores is not None and scores[i] < threshold:
                     continue
+                if math.isnan(keypoints[i][0]) or math.isnan(keypoints[i][1]):
+                    continue
                 x, y = int(keypoints[i][0]), int(keypoints[i][1])
                 if 0 <= x < W and 0 <= y < H:
                     self.draw.circle(canvas, (x, y), 4, self.colors[i % len(self.colors)], thickness=-1)
@@ -278,6 +284,8 @@ class KeypointDraw:
             for i in range(18, 24):
                 if scores is not None and scores[i] < threshold:
                     continue
+                if math.isnan(keypoints[i][0]) or math.isnan(keypoints[i][1]):
+                    continue
                 x, y = int(keypoints[i][0]), int(keypoints[i][1])
                 if 0 <= x < W and 0 <= y < H:
                     self.draw.circle(canvas, (x, y), 4, self.colors[i % len(self.colors)], thickness=-1)
@@ -291,6 +299,9 @@ class KeypointDraw:
                     if scores[idx1] < threshold or scores[idx2] < threshold:
                         continue
 
+                if math.isnan(keypoints[idx1][0]) or math.isnan(keypoints[idx1][1]) or math.isnan(keypoints[idx2][0]) or math.isnan(keypoints[idx2][1]):
+                    continue
+
                 x1, y1 = int(keypoints[idx1][0]), int(keypoints[idx1][1])
                 x2, y2 = int(keypoints[idx2][0]), int(keypoints[idx2][1])
 
@@ -305,6 +316,8 @@ class KeypointDraw:
             for i in range(92, 113):
                 if scores is not None and scores[i] < threshold:
                     continue
+                if math.isnan(keypoints[i][0]) or math.isnan(keypoints[i][1]):
+                    continue
                 x, y = int(keypoints[i][0]), int(keypoints[i][1])
                 if x > eps and y > eps and 0 <= x < W and 0 <= y < H:
                     self.draw.circle(canvas, (x, y), 4, (0, 0, 255), thickness=-1)
@@ -318,6 +331,9 @@ class KeypointDraw:
                     if scores[idx1] < threshold or scores[idx2] < threshold:
                         continue
 
+                if math.isnan(keypoints[idx1][0]) or math.isnan(keypoints[idx1][1]) or math.isnan(keypoints[idx2][0]) or math.isnan(keypoints[idx2][1]):
+                    continue
+
                 x1, y1 = int(keypoints[idx1][0]), int(keypoints[idx1][1])
                 x2, y2 = int(keypoints[idx2][0]), int(keypoints[idx2][1])
 
@@ -332,6 +348,8 @@ class KeypointDraw:
             for i in range(113, 134):
                 if scores is not None and i < len(scores) and scores[i] < threshold:
                     continue
+                if math.isnan(keypoints[i][0]) or math.isnan(keypoints[i][1]):
+                    continue
                 x, y = int(keypoints[i][0]), int(keypoints[i][1])
                 if x > eps and y > eps and 0 <= x < W and 0 <= y < H:
                     self.draw.circle(canvas, (x, y), 4, (0, 0, 255), thickness=-1)
@@ -342,6 +360,8 @@ class KeypointDraw:
             for i in range(24, 92):
                 if scores is not None and scores[i] < threshold:
                     continue
+                if math.isnan(keypoints[i][0]) or math.isnan(keypoints[i][1]):
+                    continue
                 x, y = int(keypoints[i][0]), int(keypoints[i][1])
                 if x > eps and y > eps and 0 <= x < W and 0 <= y < H:
                     self.draw.circle(canvas, (x, y), face_point_size, (255, 255, 255), thickness=-1)

extra_model_paths.yaml.example

@@ -28,7 +28,7 @@
 #config for a1111 ui
 #all you have to do is uncomment this (remove the #) and change the base_path to where yours is installed
 
-#a111:
+#a1111:
 #     base_path: path/to/stable-diffusion-webui/
 #     checkpoints: models/Stable-diffusion
 #     configs: models/Stable-diffusion

nodes.py

@@ -1754,57 +1754,49 @@ class LoadImage:
 
         return True
 
-class LoadImageMask:
+
+class LoadImageMask(LoadImage):
     ESSENTIALS_CATEGORY = "Image Tools"
     SEARCH_ALIASES = ["import mask", "alpha mask", "channel mask"]
 
     _color_channels = ["alpha", "red", "green", "blue"]
+
     @classmethod
     def INPUT_TYPES(s):
-        input_dir = folder_paths.get_input_directory()
-        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
-        return {"required":
-                    {"image": (sorted(files), {"image_upload": True}),
-                     "channel": (s._color_channels, ), }
-                }
+        types = super().INPUT_TYPES()
+        return {
+            "required": {
+                **types["required"],
+                "channel": (s._color_channels, )
+            }
+        }
 
     CATEGORY = "mask"
-
     RETURN_TYPES = ("MASK",)
-    FUNCTION = "load_image"
-    def load_image(self, image, channel):
-        image_path = folder_paths.get_annotated_filepath(image)
-        i = node_helpers.pillow(Image.open, image_path)
-        i = node_helpers.pillow(ImageOps.exif_transpose, i)
-        if i.getbands() != ("R", "G", "B", "A"):
-            if i.mode == 'I':
-                i = i.point(lambda i: i * (1 / 255))
-            i = i.convert("RGBA")
-        mask = None
+    FUNCTION = "load_image_mask"
+
+    def load_image_mask(self, image, channel):
+        image_tensor, mask_tensor = super().load_image(image)
         c = channel[0].upper()
-        if c in i.getbands():
-            mask = np.array(i.getchannel(c)).astype(np.float32) / 255.0
-            mask = torch.from_numpy(mask)
-            if c == 'A':
-                mask = 1. - mask
+
+        if c == 'A':
+            return (mask_tensor,)
+
+        channel_idx = {'R': 0, 'G': 1, 'B': 2}.get(c, 0)
+
+        if channel_idx < image_tensor.shape[-1]:
+            return (image_tensor[..., channel_idx].clone(),)
         else:
-            mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
-        return (mask.unsqueeze(0),)
+            empty_mask = torch.zeros(
+                image_tensor.shape[:-1],
+                dtype=image_tensor.dtype,
+                device=image_tensor.device
+            )
+            return (empty_mask,)
 
     @classmethod
     def IS_CHANGED(s, image, channel):
-        image_path = folder_paths.get_annotated_filepath(image)
-        m = hashlib.sha256()
-        with open(image_path, 'rb') as f:
-            m.update(f.read())
-        return m.digest().hex()
-
-    @classmethod
-    def VALIDATE_INPUTS(s, image):
-        if not folder_paths.exists_annotated_filepath(image):
-            return "Invalid image file: {}".format(image)
-
-        return True
+        return super().IS_CHANGED(image)
 
 
 class LoadImageOutput(LoadImage):

server.py

@@ -1,3 +1,4 @@
+import errno
 import os
 import sys
 import asyncio
@@ -1245,7 +1246,13 @@ class PromptServer():
             address = addr[0]
             port = addr[1]
             site = web.TCPSite(runner, address, port, ssl_context=ssl_ctx)
-            await site.start()
+            try:
+                await site.start()
+            except OSError as e:
+                if e.errno == errno.EADDRINUSE:
+                    logging.error(f"Port {port} is already in use on address {address}. Please close the other application or use a different port with --port.")
+                    raise SystemExit(1)
+                raise
 
             if not hasattr(self, 'address'):
                 self.address = address #TODO: remove this