Merge pull request #8833 from bigcat88/v3-load-save-nodes-replacement

[v3] Migrate LoadImage and SaveImage nodes to v3 schema

comfy_api/v3/io.py

@@ -202,13 +202,13 @@ class WidgetInputV3(InputV3):
         return super().as_dict_V1() | prune_dict({
             "default": self.default,
             "socketless": self.socketless,
-            "widgetType": self.widgetType,
             "forceInput": self.force_input,
         })
     
     def get_io_type_V1(self):
         return self.widgetType if self.widgetType is not None else super().get_io_type_V1()
 
+
 class OutputV3(IO_V3):
     def __init__(self, id: str, display_name: str=None, tooltip: str=None,
                  is_output_list=False):
@@ -372,7 +372,7 @@ class String(ComfyTypeIO):
     class Input(WidgetInputV3):
         '''String input.'''
         def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None, lazy: bool=None,
-                    multiline=False, placeholder: str=None, default: int=None,
+                    multiline=False, placeholder: str=None, default: str=None,
                     socketless: bool=None, force_input: bool=None):
             super().__init__(id, display_name, optional, tooltip, lazy, default, socketless, self.io_type, force_input)
             self.multiline = multiline
@@ -389,11 +389,11 @@ class String(ComfyTypeIO):
 class Combo(ComfyType):
     Type = str
     class Input(WidgetInputV3):
-        '''Combo input (dropdown).'''
+        """Combo input (dropdown)."""
         Type = str
         def __init__(self, id: str, options: list[str]=None, display_name: str=None, optional=False, tooltip: str=None, lazy: bool=None,
                     default: str=None, control_after_generate: bool=None,
-                    image_upload: bool=None, image_folder: FolderType=None,
+                    image_upload: bool=None, image_folder: FolderType=None, content_types: list[Literal["image", "video", "audio", "model"]]=None,
                     remote: RemoteOptions=None,
                     socketless: bool=None):
             super().__init__(id, display_name, optional, tooltip, lazy, default, socketless, self.io_type)
@@ -402,6 +402,7 @@ class Combo(ComfyType):
             self.control_after_generate = control_after_generate
             self.image_upload = image_upload
             self.image_folder = image_folder
+            self.content_types = content_types
             self.remote = remote
             self.default: str
 
@@ -412,6 +413,7 @@ class Combo(ComfyType):
                 "control_after_generate": self.control_after_generate,
                 "image_upload": self.image_upload,
                 "image_folder": self.image_folder.value if self.image_folder else None,
+                "content_types": self.content_types if self.content_types else None,
                 "remote": self.remote.as_dict() if self.remote else None,
             })
 
@@ -443,6 +445,20 @@ class MultiCombo(ComfyType):
 class Image(ComfyTypeIO):
     Type = torch.Tensor
 
+@comfytype(io_type="WEBCAM")
+class Webcam(ComfyTypeIO):
+    Type = str
+
+    class Input(WidgetInputV3):
+        """Webcam input."""
+        Type = str
+        def __init__(
+                self, id: str, display_name: str=None, optional=False,
+                tooltip: str=None, lazy: bool=None, default: str=None, socketless: bool=None
+        ):
+            super().__init__(id, display_name, optional, tooltip, lazy, default, socketless, self.io_type)
+
+
 @comfytype(io_type="MASK")
 class Mask(ComfyTypeIO):
     Type = torch.Tensor
@@ -969,7 +985,7 @@ class SchemaV3:
             issues.append(f"Ids must be unique between inputs and outputs, but {intersection} are not.")
         if len(issues) > 0:
             raise ValueError("\n".join(issues))
-    
+
     def finalize(self):
         """Add hidden based on selected schema options."""
         # if is an api_node, will need key-related hidden

comfy_extras/v3/nodes_images.py

@@ -0,0 +1,290 @@
+import json
+import os
+import torch
+import hashlib
+
+import numpy as np
+from PIL import Image, ImageOps, ImageSequence
+from PIL.PngImagePlugin import PngInfo
+
+from comfy_api.v3 import io, ui
+from comfy.cli_args import args
+import folder_paths
+import node_helpers
+
+
+class SaveImage_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="SaveImage_V3",
+            display_name="Save Image _V3",
+            description="Saves the input images to your ComfyUI output directory.",
+            category="image",
+            inputs=[
+                io.Image.Input(
+                    "images",
+                    display_name="images",
+                    tooltip="The images to save.",
+                ),
+                io.String.Input(
+                    "filename_prefix",
+                    default="ComfyUI",
+                    tooltip="The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes.",
+                ),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images, filename_prefix="ComfyUI"):
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
+            filename_prefix, folder_paths.get_output_directory(), images[0].shape[1], images[0].shape[0]
+        )
+        results = []
+        for (batch_number, image) in enumerate(images):
+            i = 255. * image.cpu().numpy()
+            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
+            metadata = None
+            if not args.disable_metadata:
+                metadata = PngInfo()
+                if cls.hidden.prompt is not None:
+                    metadata.add_text("prompt", json.dumps(cls.hidden.prompt))
+                if cls.hidden.extra_pnginfo is not None:
+                    for x in cls.hidden.extra_pnginfo:
+                        metadata.add_text(x, json.dumps(cls.hidden.extra_pnginfo[x]))
+
+            filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
+            file = f"{filename_with_batch_num}_{counter:05}_.png"
+            img.save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=4)
+            results.append({
+                "filename": file,
+                "subfolder": subfolder,
+                "type": "output",
+            })
+            counter += 1
+
+        return io.NodeOutput(ui={"images": results})
+
+
+class PreviewImage_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PreviewImage_V3",
+            display_name="Preview Image _V3",
+            description="Preview the input images.",
+            category="image",
+            inputs=[
+                io.Image.Input(
+                    "images",
+                    display_name="images",
+                    tooltip="The images to preview.",
+                ),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images):
+        return io.NodeOutput(ui=ui.PreviewImage(images))
+
+
+class LoadImage_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="LoadImage_V3",
+            display_name="Load Image _V3",
+            category="image",
+            inputs=[
+                io.Combo.Input(
+                    "image",
+                    display_name="image",
+                    image_upload=True,
+                    image_folder=io.FolderType.input,
+                    content_types=["image"],
+                    options=cls.get_files_options(),
+                ),
+            ],
+            outputs=[
+                io.Image.Output(
+                    "IMAGE",
+                ),
+                io.Mask.Output(
+                    "MASK",
+                ),
+            ],
+        )
+
+    @classmethod
+    def get_files_options(cls) -> list[str]:
+        target_dir = folder_paths.get_input_directory()
+        files = [f for f in os.listdir(target_dir) if os.path.isfile(os.path.join(target_dir, f))]
+        return sorted(folder_paths.filter_files_content_types(files, ["image"]))
+
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
+        img = node_helpers.pillow(Image.open, folder_paths.get_annotated_filepath(image))
+
+        output_images = []
+        output_masks = []
+        w, h = None, None
+
+        excluded_formats = ['MPO']
+
+        for i in ImageSequence.Iterator(img):
+            i = node_helpers.pillow(ImageOps.exif_transpose, i)
+
+            if i.mode == 'I':
+                i = i.point(lambda i: i * (1 / 255))
+            image = i.convert("RGB")
+
+            if len(output_images) == 0:
+                w = image.size[0]
+                h = image.size[1]
+
+            if image.size[0] != w or image.size[1] != h:
+                continue
+
+            image = np.array(image).astype(np.float32) / 255.0
+            image = torch.from_numpy(image)[None,]
+            if 'A' in i.getbands():
+                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            elif i.mode == 'P' and 'transparency' in i.info:
+                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            else:
+                mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
+            output_images.append(image)
+            output_masks.append(mask.unsqueeze(0))
+
+        if len(output_images) > 1 and img.format not in excluded_formats:
+            output_image = torch.cat(output_images, dim=0)
+            output_mask = torch.cat(output_masks, dim=0)
+        else:
+            output_image = output_images[0]
+            output_mask = output_masks[0]
+
+        return io.NodeOutput(output_image, output_mask)
+
+    @classmethod
+    def fingerprint_inputs(s, image):
+        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
+
+
+class LoadImageOutput_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="LoadImageOutput_V3",
+            display_name="Load Image (from Outputs) _V3",
+            description="Load an image from the output folder. "
+                        "When the refresh button is clicked, the node will update the image list "
+                        "and automatically select the first image, allowing for easy iteration.",
+            category="image",
+            inputs=[
+                io.Combo.Input(
+                    "image",
+                    display_name="image",
+                    image_upload=True,
+                    image_folder=io.FolderType.output,
+                    content_types=["image"],
+                    remote=io.RemoteOptions(
+                        route="/internal/files/output",
+                        refresh_button=True,
+                        control_after_refresh="first",
+                    ),
+                ),
+            ],
+            outputs=[
+                io.Image.Output(
+                    "IMAGE",
+                ),
+                io.Mask.Output(
+                    "MASK",
+                ),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
+        img = node_helpers.pillow(Image.open, folder_paths.get_annotated_filepath(image))
+
+        output_images = []
+        output_masks = []
+        w, h = None, None
+
+        excluded_formats = ['MPO']
+
+        for i in ImageSequence.Iterator(img):
+            i = node_helpers.pillow(ImageOps.exif_transpose, i)
+
+            if i.mode == 'I':
+                i = i.point(lambda i: i * (1 / 255))
+            image = i.convert("RGB")
+
+            if len(output_images) == 0:
+                w = image.size[0]
+                h = image.size[1]
+
+            if image.size[0] != w or image.size[1] != h:
+                continue
+
+            image = np.array(image).astype(np.float32) / 255.0
+            image = torch.from_numpy(image)[None,]
+            if 'A' in i.getbands():
+                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            elif i.mode == 'P' and 'transparency' in i.info:
+                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            else:
+                mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
+            output_images.append(image)
+            output_masks.append(mask.unsqueeze(0))
+
+        if len(output_images) > 1 and img.format not in excluded_formats:
+            output_image = torch.cat(output_images, dim=0)
+            output_mask = torch.cat(output_masks, dim=0)
+        else:
+            output_image = output_images[0]
+            output_mask = output_masks[0]
+
+        return io.NodeOutput(output_image, output_mask)
+
+    @classmethod
+    def fingerprint_inputs(s, image):
+        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
+
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [
+    SaveImage_V3,
+    PreviewImage_V3,
+    LoadImage_V3,
+    LoadImageOutput_V3,
+]

comfy_extras/v3/nodes_mask.py

@@ -0,0 +1,32 @@
+from comfy_api.v3 import io, ui
+
+
+class MaskPreview_V3(io.ComfyNodeV3):
+    """Mask Preview - original implement in ComfyUI_essentials.
+
+    https://github.com/cubiq/ComfyUI_essentials/blob/9d9f4bedfc9f0321c19faf71855e228c93bd0dc9/mask.py#L81
+    Upstream requested in https://github.com/Kosinkadink/rfcs/blob/main/rfcs/0000-corenodes.md#preview-nodes
+    """
+
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="MaskPreview_V3",
+            display_name="Convert Mask to Image _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input(
+                    "masks",
+                    display_name="masks",
+                ),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, masks):
+        return io.NodeOutput(ui=ui.PreviewMask(masks))
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [MaskPreview_V3]

comfy_extras/v3/nodes_webcam.py

@@ -0,0 +1,117 @@
+import hashlib
+import torch
+
+import numpy as np
+from PIL import Image, ImageOps, ImageSequence
+
+from comfy_api.v3 import io
+import nodes
+import folder_paths
+import node_helpers
+
+
+MAX_RESOLUTION = nodes.MAX_RESOLUTION
+
+
+class WebcamCapture_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="WebcamCapture_V3",
+            display_name="Webcam Capture _V3",
+            category="image",
+            inputs=[
+                io.Webcam.Input(
+                    "image",
+                    display_name="image",
+                ),
+                io.Int.Input(
+                    "width",
+                    display_name="width",
+                    default=0,
+                    min=0,
+                    max=MAX_RESOLUTION,
+                    step=1,
+                ),
+                io.Int.Input(
+                    "height",
+                    display_name="height",
+                    default=0,
+                    min=0,
+                    max=MAX_RESOLUTION,
+                    step=1,
+                ),
+                io.Boolean.Input(
+                    "capture_on_queue",
+                    default=True,
+                ),
+            ],
+            outputs=[
+                io.Image.Output(
+                    "IMAGE",
+                ),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, **kwargs) -> io.NodeOutput:
+        img = node_helpers.pillow(Image.open, folder_paths.get_annotated_filepath(image))
+
+        output_images = []
+        output_masks = []
+        w, h = None, None
+
+        excluded_formats = ['MPO']
+
+        for i in ImageSequence.Iterator(img):
+            i = node_helpers.pillow(ImageOps.exif_transpose, i)
+
+            if i.mode == 'I':
+                i = i.point(lambda i: i * (1 / 255))
+            image = i.convert("RGB")
+
+            if len(output_images) == 0:
+                w = image.size[0]
+                h = image.size[1]
+
+            if image.size[0] != w or image.size[1] != h:
+                continue
+
+            image = np.array(image).astype(np.float32) / 255.0
+            image = torch.from_numpy(image)[None,]
+            if 'A' in i.getbands():
+                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            elif i.mode == 'P' and 'transparency' in i.info:
+                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
+            else:
+                mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
+            output_images.append(image)
+            output_masks.append(mask.unsqueeze(0))
+
+        if len(output_images) > 1 and img.format not in excluded_formats:
+            output_image = torch.cat(output_images, dim=0)
+            output_mask = torch.cat(output_masks, dim=0)
+        else:
+            output_image = output_images[0]
+            output_mask = output_masks[0]
+
+        return io.NodeOutput(output_image, output_mask)
+
+    @classmethod
+    def fingerprint_inputs(s, image, width, height, capture_on_queue):
+        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
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [WebcamCapture_V3]

execution.py

@@ -321,7 +321,10 @@ def get_output_data(obj, input_data_all, execution_block_cb=None, pre_execute_cb
         elif isinstance(r, NodeOutput):
             # V3
             if r.ui is not None:
-                uis.append(r.ui.as_dict())
+                if isinstance(r.ui, dict):
+                    uis.append(r.ui)
+                else:
+                    uis.append(r.ui.as_dict())
             if r.expand is not None:
                 has_subgraph = True
                 new_graph = r.expand

nodes.py

@@ -26,7 +26,7 @@ import comfy.sd
 import comfy.utils
 import comfy.controlnet
 from comfy.comfy_types import IO, ComfyNodeABC, InputTypeDict, FileLocator
-from comfy_api.v3.io import ComfyNodeV3
+from comfy_api.v3 import io
 
 import comfy.clip_vision
 
@@ -2162,7 +2162,7 @@ def load_custom_node(module_path: str, ignore=set(), module_parent="custom_nodes
         # V3 node definition
         elif getattr(module, "NODES_LIST", None) is not None:
             for node_cls in module.NODES_LIST:
-                node_cls: ComfyNodeV3
+                node_cls: io.ComfyNodeV3
                 schema = node_cls.GET_SCHEMA()
                 if schema.node_id not in ignore:
                     NODE_CLASS_MAPPINGS[schema.node_id] = node_cls
@@ -2299,6 +2299,9 @@ def init_builtin_extra_nodes():
         "nodes_tcfg.py",
         "nodes_v3_test.py",
         "nodes_v1_test.py",
+        "v3/nodes_images.py",
+        "v3/nodes_mask.py",
+        "v3/nodes_webcam.py",
     ]
 
     import_failed = []