Merge branch 'master' into worksplit-multigpu

comfy_extras/nodes_images.py

@@ -14,6 +14,7 @@ import re
 from io import BytesIO
 from inspect import cleandoc
 import torch
+import comfy.utils
 
 from comfy.comfy_types import FileLocator
 
@@ -229,6 +230,186 @@ class SVG:
             all_svgs_list.extend(svg_item.data)
         return SVG(all_svgs_list)
 
+
+class ImageStitch:
+    """Upstreamed from https://github.com/kijai/ComfyUI-KJNodes"""
+
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "image1": ("IMAGE",),
+                "direction": (["right", "down", "left", "up"], {"default": "right"}),
+                "match_image_size": ("BOOLEAN", {"default": True}),
+                "spacing_width": (
+                    "INT",
+                    {"default": 0, "min": 0, "max": 1024, "step": 2},
+                ),
+                "spacing_color": (
+                    ["white", "black", "red", "green", "blue"],
+                    {"default": "white"},
+                ),
+            },
+            "optional": {
+                "image2": ("IMAGE",),
+            },
+        }
+
+    RETURN_TYPES = ("IMAGE",)
+    FUNCTION = "stitch"
+    CATEGORY = "image/transform"
+    DESCRIPTION = """
+Stitches image2 to image1 in the specified direction.
+If image2 is not provided, returns image1 unchanged.
+Optional spacing can be added between images.
+"""
+
+    def stitch(
+        self,
+        image1,
+        direction,
+        match_image_size,
+        spacing_width,
+        spacing_color,
+        image2=None,
+    ):
+        if image2 is None:
+            return (image1,)
+
+        # Handle batch size differences
+        if image1.shape[0] != image2.shape[0]:
+            max_batch = max(image1.shape[0], image2.shape[0])
+            if image1.shape[0] < max_batch:
+                image1 = torch.cat(
+                    [image1, image1[-1:].repeat(max_batch - image1.shape[0], 1, 1, 1)]
+                )
+            if image2.shape[0] < max_batch:
+                image2 = torch.cat(
+                    [image2, image2[-1:].repeat(max_batch - image2.shape[0], 1, 1, 1)]
+                )
+
+        # Match image sizes if requested
+        if match_image_size:
+            h1, w1 = image1.shape[1:3]
+            h2, w2 = image2.shape[1:3]
+            aspect_ratio = w2 / h2
+
+            if direction in ["left", "right"]:
+                target_h, target_w = h1, int(h1 * aspect_ratio)
+            else:  # up, down
+                target_w, target_h = w1, int(w1 / aspect_ratio)
+
+            image2 = comfy.utils.common_upscale(
+                image2.movedim(-1, 1), target_w, target_h, "lanczos", "disabled"
+            ).movedim(1, -1)
+
+        # When not matching sizes, pad to align non-concat dimensions
+        if not match_image_size:
+            h1, w1 = image1.shape[1:3]
+            h2, w2 = image2.shape[1:3]
+
+            if direction in ["left", "right"]:
+                # For horizontal concat, pad heights to match
+                if h1 != h2:
+                    target_h = max(h1, h2)
+                    if h1 < target_h:
+                        pad_h = target_h - h1
+                        pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
+                        image1 = torch.nn.functional.pad(image1, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=0.0)
+                    if h2 < target_h:
+                        pad_h = target_h - h2
+                        pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
+                        image2 = torch.nn.functional.pad(image2, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=0.0)
+            else:  # up, down
+                # For vertical concat, pad widths to match
+                if w1 != w2:
+                    target_w = max(w1, w2)
+                    if w1 < target_w:
+                        pad_w = target_w - w1
+                        pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
+                        image1 = torch.nn.functional.pad(image1, (0, 0, pad_left, pad_right), mode='constant', value=0.0)
+                    if w2 < target_w:
+                        pad_w = target_w - w2
+                        pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
+                        image2 = torch.nn.functional.pad(image2, (0, 0, pad_left, pad_right), mode='constant', value=0.0)
+
+        # Ensure same number of channels
+        if image1.shape[-1] != image2.shape[-1]:
+            max_channels = max(image1.shape[-1], image2.shape[-1])
+            if image1.shape[-1] < max_channels:
+                image1 = torch.cat(
+                    [
+                        image1,
+                        torch.ones(
+                            *image1.shape[:-1],
+                            max_channels - image1.shape[-1],
+                            device=image1.device,
+                        ),
+                    ],
+                    dim=-1,
+                )
+            if image2.shape[-1] < max_channels:
+                image2 = torch.cat(
+                    [
+                        image2,
+                        torch.ones(
+                            *image2.shape[:-1],
+                            max_channels - image2.shape[-1],
+                            device=image2.device,
+                        ),
+                    ],
+                    dim=-1,
+                )
+
+        # Add spacing if specified
+        if spacing_width > 0:
+            spacing_width = spacing_width + (spacing_width % 2)  # Ensure even
+
+            color_map = {
+                "white": 1.0,
+                "black": 0.0,
+                "red": (1.0, 0.0, 0.0),
+                "green": (0.0, 1.0, 0.0),
+                "blue": (0.0, 0.0, 1.0),
+            }
+            color_val = color_map[spacing_color]
+
+            if direction in ["left", "right"]:
+                spacing_shape = (
+                    image1.shape[0],
+                    max(image1.shape[1], image2.shape[1]),
+                    spacing_width,
+                    image1.shape[-1],
+                )
+            else:
+                spacing_shape = (
+                    image1.shape[0],
+                    spacing_width,
+                    max(image1.shape[2], image2.shape[2]),
+                    image1.shape[-1],
+                )
+
+            spacing = torch.full(spacing_shape, 0.0, device=image1.device)
+            if isinstance(color_val, tuple):
+                for i, c in enumerate(color_val):
+                    if i < spacing.shape[-1]:
+                        spacing[..., i] = c
+                if spacing.shape[-1] == 4:  # Add alpha
+                    spacing[..., 3] = 1.0
+            else:
+                spacing[..., : min(3, spacing.shape[-1])] = color_val
+                if spacing.shape[-1] == 4:
+                    spacing[..., 3] = 1.0
+
+        # Concatenate images
+        images = [image2, image1] if direction in ["left", "up"] else [image1, image2]
+        if spacing_width > 0:
+            images.insert(1, spacing)
+
+        concat_dim = 2 if direction in ["left", "right"] else 1
+        return (torch.cat(images, dim=concat_dim),)
+
+
 class SaveSVGNode:
     """
     Save SVG files on disk.
@@ -318,4 +499,5 @@ NODE_CLASS_MAPPINGS = {
     "SaveAnimatedWEBP": SaveAnimatedWEBP,
     "SaveAnimatedPNG": SaveAnimatedPNG,
     "SaveSVGNode": SaveSVGNode,
+    "ImageStitch": ImageStitch,
 }

comfy_extras/nodes_load_3d.py

@@ -16,7 +16,7 @@ class Load3D():
 
         os.makedirs(input_dir, exist_ok=True)
 
-        files = [normalize_path(os.path.join("3d", f)) for f in os.listdir(input_dir) if f.endswith(('.gltf', '.glb', '.obj', '.mtl', '.fbx', '.stl'))]
+        files = [normalize_path(os.path.join("3d", f)) for f in os.listdir(input_dir) if f.endswith(('.gltf', '.glb', '.obj', '.fbx', '.stl'))]
 
         return {"required": {
             "model_file": (sorted(files), {"file_upload": True}),

comfy_extras/nodes_string.py

@@ -296,6 +296,41 @@ class RegexExtract():
 
         return result,
 
+
+class RegexReplace():
+    DESCRIPTION = "Find and replace text using regex patterns."
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "string": (IO.STRING, {"multiline": True}),
+                "regex_pattern": (IO.STRING, {"multiline": True}),
+                "replace": (IO.STRING, {"multiline": True}),
+            },
+            "optional": {
+                "case_insensitive": (IO.BOOLEAN, {"default": True}),
+                "multiline": (IO.BOOLEAN, {"default": False}),
+                "dotall": (IO.BOOLEAN, {"default": False, "tooltip": "When enabled, the dot (.) character will match any character including newline characters. When disabled, dots won't match newlines."}),
+                "count": (IO.INT, {"default": 0, "min": 0, "max": 100, "tooltip": "Maximum number of replacements to make. Set to 0 to replace all occurrences (default). Set to 1 to replace only the first match, 2 for the first two matches, etc."}),
+            }
+        }
+
+    RETURN_TYPES = (IO.STRING,)
+    FUNCTION = "execute"
+    CATEGORY = "utils/string"
+
+    def execute(self, string, regex_pattern, replace, case_insensitive=True, multiline=False, dotall=False, count=0, **kwargs):
+        flags = 0
+
+        if case_insensitive:
+            flags |= re.IGNORECASE
+        if multiline:
+            flags |= re.MULTILINE
+        if dotall:
+            flags |= re.DOTALL
+        result = re.sub(regex_pattern, replace, string, count=count, flags=flags)
+        return result,
+
 NODE_CLASS_MAPPINGS = {
     "StringConcatenate": StringConcatenate,
     "StringSubstring": StringSubstring,
@@ -306,7 +341,8 @@ NODE_CLASS_MAPPINGS = {
     "StringContains": StringContains,
     "StringCompare": StringCompare,
     "RegexMatch": RegexMatch,
-    "RegexExtract": RegexExtract
+    "RegexExtract": RegexExtract,
+    "RegexReplace": RegexReplace,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -319,5 +355,6 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "StringContains": "Contains",
     "StringCompare": "Compare",
     "RegexMatch": "Regex Match",
-    "RegexExtract": "Regex Extract"
+    "RegexExtract": "Regex Extract",
+    "RegexReplace": "Regex Replace",
 }

comfy_extras/nodes_wan.py

@@ -268,8 +268,9 @@ class WanVaceToVideo:
             trim_latent = reference_image.shape[2]
 
         mask = mask.unsqueeze(0)
-        positive = node_helpers.conditioning_set_values(positive, {"vace_frames": control_video_latent, "vace_mask": mask, "vace_strength": strength})
-        negative = node_helpers.conditioning_set_values(negative, {"vace_frames": control_video_latent, "vace_mask": mask, "vace_strength": strength})
+
+        positive = node_helpers.conditioning_set_values(positive, {"vace_frames": [control_video_latent], "vace_mask": [mask], "vace_strength": [strength]}, append=True)
+        negative = node_helpers.conditioning_set_values(negative, {"vace_frames": [control_video_latent], "vace_mask": [mask], "vace_strength": [strength]}, append=True)
 
         latent = torch.zeros([batch_size, 16, latent_length, height // 8, width // 8], device=comfy.model_management.intermediate_device())
         out_latent = {}
@@ -344,6 +345,44 @@ class WanCameraImageToVideo:
         out_latent["samples"] = latent
         return (positive, negative, out_latent)
 
+class WanPhantomSubjectToVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"positive": ("CONDITIONING", ),
+                             "negative": ("CONDITIONING", ),
+                             "vae": ("VAE", ),
+                             "width": ("INT", {"default": 832, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "length": ("INT", {"default": 81, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
+                             "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
+                },
+                "optional": {"images": ("IMAGE", ),
+                }}
+
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "negative_text", "negative_img_text", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/video_models"
+
+    def encode(self, positive, negative, vae, width, height, length, batch_size, images):
+        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        cond2 = negative
+        if images is not None:
+            images = comfy.utils.common_upscale(images[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+            latent_images = []
+            for i in images:
+                latent_images += [vae.encode(i.unsqueeze(0)[:, :, :, :3])]
+            concat_latent_image = torch.cat(latent_images, dim=2)
+
+            positive = node_helpers.conditioning_set_values(positive, {"time_dim_concat": concat_latent_image})
+            cond2 = node_helpers.conditioning_set_values(negative, {"time_dim_concat": concat_latent_image})
+            negative = node_helpers.conditioning_set_values(negative, {"time_dim_concat": comfy.latent_formats.Wan21().process_out(torch.zeros_like(concat_latent_image))})
+
+        out_latent = {}
+        out_latent["samples"] = latent
+        return (positive, cond2, negative, out_latent)
+
 NODE_CLASS_MAPPINGS = {
     "WanImageToVideo": WanImageToVideo,
     "WanFunControlToVideo": WanFunControlToVideo,
@@ -352,4 +391,5 @@ NODE_CLASS_MAPPINGS = {
     "WanVaceToVideo": WanVaceToVideo,
     "TrimVideoLatent": TrimVideoLatent,
     "WanCameraImageToVideo": WanCameraImageToVideo,
+    "WanPhantomSubjectToVideo": WanPhantomSubjectToVideo,
 }