Merge remote-tracking branch 'upstream/master' into sam3d_body

comfy_api_nodes/nodes_openai.py

@@ -9,6 +9,7 @@ from PIL import Image
 from typing_extensions import override
 
 import folder_paths
+from comfy.utils import common_upscale
 from comfy_api.latest import IO, ComfyExtension, Input
 from comfy_api_nodes.apis.openai import (
     InputFileContent,
@@ -62,7 +63,8 @@ async def validate_and_cast_response(response, timeout: int = None) -> torch.Ten
         timeout: Request timeout in seconds. Defaults to None (no timeout).
 
     Returns:
-        A torch.Tensor representing the image (1, H, W, C).
+        A torch.Tensor of shape (N, H, W, C) with all returned images; images whose
+        dimensions differ from the first image's are resized to match it.
 
     Raises:
         ValueError: If the response is not valid.
@@ -89,6 +91,14 @@ async def validate_and_cast_response(response, timeout: int = None) -> torch.Ten
         arr = np.asarray(pil_img).astype(np.float32) / 255.0
         image_tensors.append(torch.from_numpy(arr))
 
+    # With size="auto" the API can return images whose dimensions differ by a few pixels within a single response
+    # resize them to the first image's dimensions so they can be stacked into one batch.
+    ref_h, ref_w = image_tensors[0].shape[:2]
+    for i, t in enumerate(image_tensors):
+        if t.shape[:2] != (ref_h, ref_w):
+            samples = t.unsqueeze(0).movedim(-1, 1)
+            samples = common_upscale(samples, ref_w, ref_h, "bilinear", "center")
+            image_tensors[i] = samples.movedim(1, -1).squeeze(0)
     return torch.stack(image_tensors, dim=0)
 
 

comfy_extras/nodes_scail.py

@@ -267,7 +267,8 @@ class SCAIL2ColoredMask(io.ComfyNode):
                 io.Combo.Input("sort_by", options=["none", "left_to_right", "area"], default="left_to_right",
                                tooltip="Order in which palette colors are assigned to the tracked objects (applied to both reference and pose video so each identity keeps the same color). left_to_right = leftmost object (by first-frame centroid) gets the first color; area = biggest object (by first-frame mask area) gets the first color; none = keep SAM3's order."),
                 io.Boolean.Input("replacement_mode", default=False,
-                                 tooltip="False = mask_video has black bg (Animation Mode). True = white bg (Replacement Mode). Set the matching replacement_mode on WanSCAILToVideo. reference_image_mask is always black-bg regardless."),
+                                 tooltip="False = Animation Mode (pose_video_mask has black background, reference_image_mask has white background). "
+                                         "True = Replacement Mode (pose_video_mask has white background, reference_image_mask has black background)."),
             ],
             outputs=[
                 io.Image.Output("pose_video_mask"),
@@ -296,14 +297,17 @@ class SCAIL2ColoredMask(io.ComfyNode):
             return td
 
         drv = _prep(driving_track_data)
+        # Animation: driving=black, ref=white. Replacement: driving=white, ref=black.
         mask_video = _render_colored_masks(drv, "white" if replacement_mode else "black")
+        ref_bg = "black" if replacement_mode else "white"
 
         if ref_track_data is not None:
             ref = _prep(ref_track_data)
-            reference_image_mask = _render_colored_masks(ref, "black")
+            reference_image_mask = _render_colored_masks(ref, ref_bg)
         else:
             H, W = drv["orig_size"]
-            reference_image_mask = torch.zeros(1, H, W, 3, device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
+            fill_value = 1.0 if ref_bg == "white" else 0.0
+            reference_image_mask = torch.full((1, H, W, 3), fill_value, device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
 
         return io.NodeOutput(mask_video, reference_image_mask)