Removed code for a couple test nodes in nodes_logic.py

* converted nodes_images.py to V3 schema

* fix test

README.md

@@ -212,6 +212,8 @@ Python 3.14 works but you may encounter issues with the torch compile node. The
 
 Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12
 
+torch 2.4 and above is supported but some features might only work on newer versions. We generally recommend using the latest major version of pytorch unless it is less than 2 weeks old.
+
 ### Instructions:
 
 Git clone this repo.

comfy/k_diffusion/sampling.py

@@ -74,6 +74,9 @@ def get_ancestral_step(sigma_from, sigma_to, eta=1.):
 
 def default_noise_sampler(x, seed=None):
     if seed is not None:
+        if x.device == torch.device("cpu"):
+            seed += 1
+
         generator = torch.Generator(device=x.device)
         generator.manual_seed(seed)
     else:

comfy_api/latest/_io.py

@@ -27,9 +27,8 @@ if TYPE_CHECKING:
 from comfy_api.internal import (_ComfyNodeInternal, _NodeOutputInternal, classproperty, copy_class, first_real_override, is_class,
     prune_dict, shallow_clone_class)
 from comfy_execution.graph_utils import ExecutionBlocker
-from ._util import MESH, VOXEL
+from ._util import MESH, VOXEL, SVG as _SVG
 
-# from comfy_extras.nodes_images import SVG as SVG_ # NOTE: needs to be moved before can be imported due to circular reference
 
 class FolderType(str, Enum):
     input = "input"
@@ -208,13 +207,14 @@ class Output(_IO_V3):
     def __init__(self, id: str=None, display_name: str=None, tooltip: str=None,
                  is_output_list=False):
         self.id = id
-        self.display_name = display_name
+        self.display_name = display_name if display_name else id
         self.tooltip = tooltip
         self.is_output_list = is_output_list
 
     def as_dict(self):
+        display_name = self.display_name if self.display_name else self.id
         return prune_dict({
-            "display_name": self.display_name,
+            "display_name": display_name,
             "tooltip": self.tooltip,
             "is_output_list": self.is_output_list,
         })
@@ -644,7 +644,7 @@ class Video(ComfyTypeIO):
 
 @comfytype(io_type="SVG")
 class SVG(ComfyTypeIO):
-    Type = Any # TODO: SVG class is defined in comfy_extras/nodes_images.py, causing circular reference; should be moved to somewhere else before referenced directly in v3
+    Type = _SVG
 
 @comfytype(io_type="LORA_MODEL")
 class LoraModel(ComfyTypeIO):
@@ -853,8 +853,10 @@ class MatchType(ComfyTypeIO):
             })
 
     class Output(Output):
-        def __init__(self, template: MatchType.Template, id: str=None, display_name: str="MATCHTYPE", tooltip: str=None,
+        def __init__(self, template: MatchType.Template, id: str=None, display_name: str=None, tooltip: str=None,
                      is_output_list=False):
+            if not id and not display_name:
+                display_name = "MATCHTYPE"
             super().__init__(id, display_name, tooltip, is_output_list)
             self.template = template
 
@@ -1287,16 +1289,12 @@ class Schema:
         output_ids = [o.id for o in self.outputs]
         input_set = set(input_ids)
         output_set = set(output_ids)
-        issues = []
+        issues: list[str] = []
         # verify ids are unique per list
         if len(input_set) != len(input_ids):
             issues.append(f"Input ids must be unique, but {[item for item, count in Counter(input_ids).items() if count > 1]} are not.")
         if len(output_set) != len(output_ids):
             issues.append(f"Output ids must be unique, but {[item for item, count in Counter(output_ids).items() if count > 1]} are not.")
-        # verify ids are unique between lists
-        intersection = input_set & output_set
-        if len(intersection) > 0:
-            issues.append(f"Ids must be unique between inputs and outputs, but {intersection} are not.")
         if len(issues) > 0:
             raise ValueError("\n".join(issues))
         # validate inputs and outputs
@@ -1948,7 +1946,7 @@ __all__ = [
     # Dynamic Types
     "MatchType",
     "DynamicCombo",
-    # "Autogrow",
+    "Autogrow",
     # Other classes
     "HiddenHolder",
     "Hidden",

comfy_api/latest/_util/__init__.py

@@ -1,5 +1,6 @@
 from .video_types import VideoContainer, VideoCodec, VideoComponents
 from .geometry_types import VOXEL, MESH
+from .image_types import SVG
 
 __all__ = [
     # Utility Types
@@ -8,4 +9,5 @@ __all__ = [
     "VideoComponents",
     "VOXEL",
     "MESH",
+    "SVG",
 ]

comfy_api/latest/_util/image_types.py

@@ -0,0 +1,18 @@
+from io import BytesIO
+
+
+class SVG:
+    """Stores SVG representations via a list of BytesIO objects."""
+
+    def __init__(self, data: list[BytesIO]):
+        self.data = data
+
+    def combine(self, other: 'SVG') -> 'SVG':
+        return SVG(self.data + other.data)
+
+    @staticmethod
+    def combine_all(svgs: list['SVG']) -> 'SVG':
+        all_svgs_list: list[BytesIO] = []
+        for svg_item in svgs:
+            all_svgs_list.extend(svg_item.data)
+        return SVG(all_svgs_list)

comfy_api_nodes/apis/gemini_api.py

@@ -133,6 +133,7 @@ class GeminiImageGenerateContentRequest(BaseModel):
     systemInstruction: GeminiSystemInstructionContent | None = Field(None)
     tools: list[GeminiTool] | None = Field(None)
     videoMetadata: GeminiVideoMetadata | None = Field(None)
+    uploadImagesToStorage: bool = Field(True)
 
 
 class GeminiGenerateContentRequest(BaseModel):

comfy_api_nodes/apis/kling_api.py

@@ -102,3 +102,12 @@ class ImageToVideoWithAudioRequest(BaseModel):
     prompt: str = Field(...)
     mode: str = Field("pro")
     sound: str = Field(..., description="'on' or 'off'")
+
+
+class MotionControlRequest(BaseModel):
+    prompt: str = Field(...)
+    image_url: str = Field(...)
+    video_url: str = Field(...)
+    keep_original_sound: str = Field(...)
+    character_orientation: str = Field(...)
+    mode: str = Field(..., description="'pro' or 'std'")

comfy_api_nodes/nodes_gemini.py

@@ -34,6 +34,7 @@ from comfy_api_nodes.util import (
     ApiEndpoint,
     audio_to_base64_string,
     bytesio_to_image_tensor,
+    download_url_to_image_tensor,
     get_number_of_images,
     sync_op,
     tensor_to_base64_string,
@@ -141,9 +142,11 @@ def get_parts_by_type(response: GeminiGenerateContentResponse, part_type: Litera
         )
     parts = []
     for part in response.candidates[0].content.parts:
-        if part_type == "text" and hasattr(part, "text") and part.text:
+        if part_type == "text" and part.text:
             parts.append(part)
-        elif hasattr(part, "inlineData") and part.inlineData and part.inlineData.mimeType == part_type:
+        elif part.inlineData and part.inlineData.mimeType == part_type:
+            parts.append(part)
+        elif part.fileData and part.fileData.mimeType == part_type:
             parts.append(part)
         # Skip parts that don't match the requested type
     return parts
@@ -163,12 +166,15 @@ def get_text_from_response(response: GeminiGenerateContentResponse) -> str:
     return "\n".join([part.text for part in parts])
 
 
-def get_image_from_response(response: GeminiGenerateContentResponse) -> Input.Image:
+async def get_image_from_response(response: GeminiGenerateContentResponse) -> Input.Image:
     image_tensors: list[Input.Image] = []
     parts = get_parts_by_type(response, "image/png")
     for part in parts:
-        image_data = base64.b64decode(part.inlineData.data)
-        returned_image = bytesio_to_image_tensor(BytesIO(image_data))
+        if part.inlineData:
+            image_data = base64.b64decode(part.inlineData.data)
+            returned_image = bytesio_to_image_tensor(BytesIO(image_data))
+        else:
+            returned_image = await download_url_to_image_tensor(part.fileData.fileUri)
         image_tensors.append(returned_image)
     if len(image_tensors) == 0:
         return torch.zeros((1, 1024, 1024, 4))
@@ -596,7 +602,7 @@ class GeminiImage(IO.ComfyNode):
 
         response = await sync_op(
             cls,
-            endpoint=ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model}", method="POST"),
+            ApiEndpoint(path=f"/proxy/vertexai/gemini/{model}", method="POST"),
             data=GeminiImageGenerateContentRequest(
                 contents=[
                     GeminiContent(role=GeminiRole.user, parts=parts),
@@ -610,7 +616,7 @@ class GeminiImage(IO.ComfyNode):
             response_model=GeminiGenerateContentResponse,
             price_extractor=calculate_tokens_price,
         )
-        return IO.NodeOutput(get_image_from_response(response), get_text_from_response(response))
+        return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response))
 
 
 class GeminiImage2(IO.ComfyNode):
@@ -729,7 +735,7 @@ class GeminiImage2(IO.ComfyNode):
 
         response = await sync_op(
             cls,
-            ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model}", method="POST"),
+            ApiEndpoint(path=f"/proxy/vertexai/gemini/{model}", method="POST"),
             data=GeminiImageGenerateContentRequest(
                 contents=[
                     GeminiContent(role=GeminiRole.user, parts=parts),
@@ -743,7 +749,7 @@ class GeminiImage2(IO.ComfyNode):
             response_model=GeminiGenerateContentResponse,
             price_extractor=calculate_tokens_price,
         )
-        return IO.NodeOutput(get_image_from_response(response), get_text_from_response(response))
+        return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response))
 
 
 class GeminiExtension(ComfyExtension):

comfy_api_nodes/nodes_kling.py

@@ -51,6 +51,7 @@ from comfy_api_nodes.apis import (
 )
 from comfy_api_nodes.apis.kling_api import (
     ImageToVideoWithAudioRequest,
+    MotionControlRequest,
     OmniImageParamImage,
     OmniParamImage,
     OmniParamVideo,
@@ -2163,6 +2164,91 @@ class ImageToVideoWithAudio(IO.ComfyNode):
         return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
 
 
+class MotionControl(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="KlingMotionControl",
+            display_name="Kling Motion Control",
+            category="api node/video/Kling",
+            inputs=[
+                IO.String.Input("prompt", multiline=True),
+                IO.Image.Input("reference_image"),
+                IO.Video.Input(
+                    "reference_video",
+                    tooltip="Motion reference video used to drive movement/expression.\n"
+                    "Duration limits depend on character_orientation:\n"
+                    " - image: 3–10s (max 10s)\n"
+                    " - video: 3–30s (max 30s)",
+                ),
+                IO.Boolean.Input("keep_original_sound", default=True),
+                IO.Combo.Input(
+                    "character_orientation",
+                    options=["video", "image"],
+                    tooltip="Controls where the character's facing/orientation comes from.\n"
+                    "video: movements, expressions, camera moves, and orientation "
+                    "follow the motion reference video (other details via prompt).\n"
+                    "image: movements and expressions still follow the motion reference video, "
+                    "but the character orientation matches the reference image (camera/other details via prompt).",
+                ),
+                IO.Combo.Input("mode", options=["pro", "std"]),
+            ],
+            outputs=[
+                IO.Video.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        prompt: str,
+        reference_image: Input.Image,
+        reference_video: Input.Video,
+        keep_original_sound: bool,
+        character_orientation: str,
+        mode: str,
+    ) -> IO.NodeOutput:
+        validate_string(prompt, max_length=2500)
+        validate_image_dimensions(reference_image, min_width=340, min_height=340)
+        validate_image_aspect_ratio(reference_image, (1, 2.5), (2.5, 1))
+        if character_orientation == "image":
+            validate_video_duration(reference_video, min_duration=3, max_duration=10)
+        else:
+            validate_video_duration(reference_video, min_duration=3, max_duration=30)
+        validate_video_dimensions(reference_video, min_width=340, min_height=340, max_width=3850, max_height=3850)
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/kling/v1/videos/motion-control", method="POST"),
+            response_model=TaskStatusResponse,
+            data=MotionControlRequest(
+                prompt=prompt,
+                image_url=(await upload_images_to_comfyapi(cls, reference_image))[0],
+                video_url=await upload_video_to_comfyapi(cls, reference_video),
+                keep_original_sound="yes" if keep_original_sound else "no",
+                character_orientation=character_orientation,
+                mode=mode,
+            ),
+        )
+        if response.code:
+            raise RuntimeError(
+                f"Kling request failed. Code: {response.code}, Message: {response.message}, Data: {response.data}"
+            )
+        final_response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/kling/v1/videos/motion-control/{response.data.task_id}"),
+            response_model=TaskStatusResponse,
+            status_extractor=lambda r: (r.data.task_status if r.data else None),
+        )
+        return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
+
+
 class KlingExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -2188,6 +2274,7 @@ class KlingExtension(ComfyExtension):
             OmniProImageNode,
             TextToVideoWithAudio,
             ImageToVideoWithAudio,
+            MotionControl,
         ]
 
 

comfy_extras/nodes_custom_sampler.py

@@ -9,6 +9,7 @@ import comfy.utils
 import node_helpers
 from typing_extensions import override
 from comfy_api.latest import ComfyExtension, io
+import re
 
 
 class BasicScheduler(io.ComfyNode):
@@ -1013,6 +1014,25 @@ class AddNoise(io.ComfyNode):
 
     add_noise = execute
 
+class ManualSigmas(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ManualSigmas",
+            category="_for_testing/custom_sampling",
+            is_experimental=True,
+            inputs=[
+                io.String.Input("sigmas", default="1, 0.5", multiline=False)
+            ],
+            outputs=[io.Sigmas.Output()]
+        )
+
+    @classmethod
+    def execute(cls, sigmas) -> io.NodeOutput:
+        sigmas = re.findall(r"[-+]?(?:\d*\.*\d+)", sigmas)
+        sigmas = [float(i) for i in sigmas]
+        sigmas = torch.FloatTensor(sigmas)
+        return io.NodeOutput(sigmas)
 
 class CustomSamplersExtension(ComfyExtension):
     @override
@@ -1052,6 +1072,7 @@ class CustomSamplersExtension(ComfyExtension):
             DisableNoise,
             AddNoise,
             SamplerCustomAdvanced,
+            ManualSigmas,
         ]
 
 

comfy_extras/nodes_images.py

@@ -2,280 +2,231 @@ from __future__ import annotations
 
 import nodes
 import folder_paths
-from comfy.cli_args import args
 
-from PIL import Image
-from PIL.PngImagePlugin import PngInfo
-
-import numpy as np
 import json
 import os
 import re
-from io import BytesIO
-from inspect import cleandoc
 import torch
 import comfy.utils
 
-from comfy.comfy_types import FileLocator, IO
 from server import PromptServer
+from comfy_api.latest import ComfyExtension, IO, UI
+from typing_extensions import override
+
+SVG = IO.SVG.Type  # TODO: temporary solution for backward compatibility, will be removed later.
 
 MAX_RESOLUTION = nodes.MAX_RESOLUTION
 
-class ImageCrop:
+class ImageCrop(IO.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",),
-                              "width": ("INT", {"default": 512, "min": 1, "max": MAX_RESOLUTION, "step": 1}),
-                              "height": ("INT", {"default": 512, "min": 1, "max": MAX_RESOLUTION, "step": 1}),
-                              "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
-                              "y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
-                              }}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "crop"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageCrop",
+            display_name="Image Crop",
+            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),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/transform"
-
-    def crop(self, image, width, height, x, y):
+    @classmethod
+    def execute(cls, image, width, height, x, y) -> IO.NodeOutput:
         x = min(x, image.shape[2] - 1)
         y = min(y, image.shape[1] - 1)
         to_x = width + x
         to_y = height + y
         img = image[:,y:to_y, x:to_x, :]
-        return (img,)
+        return IO.NodeOutput(img)
 
-class RepeatImageBatch:
+    crop = execute  # TODO: remove
+
+
+class RepeatImageBatch(IO.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",),
-                              "amount": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              }}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "repeat"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="RepeatImageBatch",
+            category="image/batch",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Int.Input("amount", default=1, min=1, max=4096),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/batch"
-
-    def repeat(self, image, amount):
+    @classmethod
+    def execute(cls, image, amount) -> IO.NodeOutput:
         s = image.repeat((amount, 1,1,1))
-        return (s,)
+        return IO.NodeOutput(s)
 
-class ImageFromBatch:
+    repeat = execute  # TODO: remove
+
+
+class ImageFromBatch(IO.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",),
-                              "batch_index": ("INT", {"default": 0, "min": 0, "max": 4095}),
-                              "length": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              }}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "frombatch"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageFromBatch",
+            category="image/batch",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Int.Input("batch_index", default=0, min=0, max=4095),
+                IO.Int.Input("length", default=1, min=1, max=4096),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/batch"
-
-    def frombatch(self, image, batch_index, length):
+    @classmethod
+    def execute(cls, image, batch_index, length) -> IO.NodeOutput:
         s_in = image
         batch_index = min(s_in.shape[0] - 1, batch_index)
         length = min(s_in.shape[0] - batch_index, length)
         s = s_in[batch_index:batch_index + length].clone()
-        return (s,)
+        return IO.NodeOutput(s)
+
+    frombatch = execute  # TODO: remove
 
 
-class ImageAddNoise:
+class ImageAddNoise(IO.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",),
-                              "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "control_after_generate": True, "tooltip": "The random seed used for creating the noise."}),
-                              "strength": ("FLOAT", {"default": 0.5, "min": 0.0, "max": 1.0, "step": 0.01}),
-                              }}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "repeat"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageAddNoise",
+            category="image",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="The random seed used for creating the noise.",
+                ),
+                IO.Float.Input("strength", default=0.5, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image"
-
-    def repeat(self, image, seed, strength):
+    @classmethod
+    def execute(cls, image, seed, strength) -> IO.NodeOutput:
         generator = torch.manual_seed(seed)
         s = torch.clip((image + strength * torch.randn(image.size(), generator=generator, device="cpu").to(image)), min=0.0, max=1.0)
-        return (s,)
+        return IO.NodeOutput(s)
 
-class SaveAnimatedWEBP:
-    def __init__(self):
-        self.output_dir = folder_paths.get_output_directory()
-        self.type = "output"
-        self.prefix_append = ""
+    repeat = execute  # TODO: remove
 
-    methods = {"default": 4, "fastest": 0, "slowest": 6}
-    @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"images": ("IMAGE", ),
-                     "filename_prefix": ("STRING", {"default": "ComfyUI"}),
-                     "fps": ("FLOAT", {"default": 6.0, "min": 0.01, "max": 1000.0, "step": 0.01}),
-                     "lossless": ("BOOLEAN", {"default": True}),
-                     "quality": ("INT", {"default": 80, "min": 0, "max": 100}),
-                     "method": (list(s.methods.keys()),),
-                     # "num_frames": ("INT", {"default": 0, "min": 0, "max": 8192}),
-                     },
-                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
-                }
 
-    RETURN_TYPES = ()
-    FUNCTION = "save_images"
-
-    OUTPUT_NODE = True
-
-    CATEGORY = "image/animation"
-
-    def save_images(self, images, fps, filename_prefix, lossless, quality, method, num_frames=0, prompt=None, extra_pnginfo=None):
-        method = self.methods.get(method)
-        filename_prefix += self.prefix_append
-        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
-        results: list[FileLocator] = []
-        pil_images = []
-        for image in images:
-            i = 255. * image.cpu().numpy()
-            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
-            pil_images.append(img)
-
-        metadata = pil_images[0].getexif()
-        if not args.disable_metadata:
-            if prompt is not None:
-                metadata[0x0110] = "prompt:{}".format(json.dumps(prompt))
-            if extra_pnginfo is not None:
-                inital_exif = 0x010f
-                for x in extra_pnginfo:
-                    metadata[inital_exif] = "{}:{}".format(x, json.dumps(extra_pnginfo[x]))
-                    inital_exif -= 1
-
-        if num_frames == 0:
-            num_frames = len(pil_images)
-
-        c = len(pil_images)
-        for i in range(0, c, num_frames):
-            file = f"{filename}_{counter:05}_.webp"
-            pil_images[i].save(os.path.join(full_output_folder, file), save_all=True, duration=int(1000.0/fps), append_images=pil_images[i + 1:i + num_frames], exif=metadata, lossless=lossless, quality=quality, method=method)
-            results.append({
-                "filename": file,
-                "subfolder": subfolder,
-                "type": self.type
-            })
-            counter += 1
-
-        animated = num_frames != 1
-        return { "ui": { "images": results, "animated": (animated,) } }
-
-class SaveAnimatedPNG:
-    def __init__(self):
-        self.output_dir = folder_paths.get_output_directory()
-        self.type = "output"
-        self.prefix_append = ""
+class SaveAnimatedWEBP(IO.ComfyNode):
+    COMPRESS_METHODS = {"default": 4, "fastest": 0, "slowest": 6}
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"images": ("IMAGE", ),
-                     "filename_prefix": ("STRING", {"default": "ComfyUI"}),
-                     "fps": ("FLOAT", {"default": 6.0, "min": 0.01, "max": 1000.0, "step": 0.01}),
-                     "compress_level": ("INT", {"default": 4, "min": 0, "max": 9})
-                     },
-                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
-                }
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="SaveAnimatedWEBP",
+            category="image/animation",
+            inputs=[
+                IO.Image.Input("images"),
+                IO.String.Input("filename_prefix", default="ComfyUI"),
+                IO.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
+                IO.Boolean.Input("lossless", default=True),
+                IO.Int.Input("quality", default=80, min=0, max=100),
+                IO.Combo.Input("method", options=list(cls.COMPRESS_METHODS.keys())),
+                # "num_frames": ("INT", {"default": 0, "min": 0, "max": 8192}),
+            ],
+            hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
 
-    RETURN_TYPES = ()
-    FUNCTION = "save_images"
+    @classmethod
+    def execute(cls, images, fps, filename_prefix, lossless, quality, method, num_frames=0) -> IO.NodeOutput:
+        return IO.NodeOutput(
+            ui=UI.ImageSaveHelper.get_save_animated_webp_ui(
+                images=images,
+                filename_prefix=filename_prefix,
+                cls=cls,
+                fps=fps,
+                lossless=lossless,
+                quality=quality,
+                method=cls.COMPRESS_METHODS.get(method)
+            )
+        )
 
-    OUTPUT_NODE = True
-
-    CATEGORY = "image/animation"
-
-    def save_images(self, images, fps, compress_level, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
-        filename_prefix += self.prefix_append
-        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
-        results = list()
-        pil_images = []
-        for image in images:
-            i = 255. * image.cpu().numpy()
-            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
-            pil_images.append(img)
-
-        metadata = None
-        if not args.disable_metadata:
-            metadata = PngInfo()
-            if prompt is not None:
-                metadata.add(b"comf", "prompt".encode("latin-1", "strict") + b"\0" + json.dumps(prompt).encode("latin-1", "strict"), after_idat=True)
-            if extra_pnginfo is not None:
-                for x in extra_pnginfo:
-                    metadata.add(b"comf", x.encode("latin-1", "strict") + b"\0" + json.dumps(extra_pnginfo[x]).encode("latin-1", "strict"), after_idat=True)
-
-        file = f"{filename}_{counter:05}_.png"
-        pil_images[0].save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=compress_level, save_all=True, duration=int(1000.0/fps), append_images=pil_images[1:])
-        results.append({
-            "filename": file,
-            "subfolder": subfolder,
-            "type": self.type
-        })
-
-        return { "ui": { "images": results, "animated": (True,)} }
-
-class SVG:
-    """
-    Stores SVG representations via a list of BytesIO objects.
-    """
-    def __init__(self, data: list[BytesIO]):
-        self.data = data
-
-    def combine(self, other: 'SVG') -> 'SVG':
-        return SVG(self.data + other.data)
-
-    @staticmethod
-    def combine_all(svgs: list['SVG']) -> 'SVG':
-        all_svgs_list: list[BytesIO] = []
-        for svg_item in svgs:
-            all_svgs_list.extend(svg_item.data)
-        return SVG(all_svgs_list)
+    save_images = execute  # TODO: remove
 
 
-class ImageStitch:
+class SaveAnimatedPNG(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="SaveAnimatedPNG",
+            category="image/animation",
+            inputs=[
+                IO.Image.Input("images"),
+                IO.String.Input("filename_prefix", default="ComfyUI"),
+                IO.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
+                IO.Int.Input("compress_level", default=4, min=0, max=9),
+            ],
+            hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images, fps, compress_level, filename_prefix="ComfyUI") -> IO.NodeOutput:
+        return IO.NodeOutput(
+            ui=UI.ImageSaveHelper.get_save_animated_png_ui(
+                images=images,
+                filename_prefix=filename_prefix,
+                cls=cls,
+                fps=fps,
+                compress_level=compress_level,
+            )
+        )
+
+    save_images = execute  # TODO: remove
+
+
+class ImageStitch(IO.ComfyNode):
     """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",),
-            },
-        }
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageStitch",
+            display_name="Image Stitch",
+            description="Stitches image2 to image1 in the specified direction.\n"
+            "If image2 is not provided, returns image1 unchanged.\n"
+            "Optional spacing can be added between images.",
+            category="image/transform",
+            inputs=[
+                IO.Image.Input("image1"),
+                IO.Combo.Input("direction", options=["right", "down", "left", "up"], default="right"),
+                IO.Boolean.Input("match_image_size", default=True),
+                IO.Int.Input("spacing_width", default=0, min=0, max=1024, step=2),
+                IO.Combo.Input("spacing_color", options=["white", "black", "red", "green", "blue"], default="white"),
+                IO.Image.Input("image2", optional=True),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    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,
+    @classmethod
+    def execute(
+        cls,
         image1,
         direction,
         match_image_size,
         spacing_width,
         spacing_color,
         image2=None,
-    ):
+    ) -> IO.NodeOutput:
         if image2 is None:
-            return (image1,)
+            return IO.NodeOutput(image1)
 
         # Handle batch size differences
         if image1.shape[0] != image2.shape[0]:
@@ -412,36 +363,30 @@ Optional spacing can be added between images.
             images.insert(1, spacing)
 
         concat_dim = 2 if direction in ["left", "right"] else 1
-        return (torch.cat(images, dim=concat_dim),)
+        return IO.NodeOutput(torch.cat(images, dim=concat_dim))
+
+    stitch = execute  # TODO: remove
+
+
+class ResizeAndPadImage(IO.ComfyNode):
 
-class ResizeAndPadImage:
     @classmethod
-    def INPUT_TYPES(cls):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "target_width": ("INT", {
-                    "default": 512,
-                    "min": 1,
-                    "max": MAX_RESOLUTION,
-                    "step": 1
-                }),
-                "target_height": ("INT", {
-                    "default": 512,
-                    "min": 1,
-                    "max": MAX_RESOLUTION,
-                    "step": 1
-                }),
-                "padding_color": (["white", "black"],),
-                "interpolation": (["area", "bicubic", "nearest-exact", "bilinear", "lanczos"],),
-            }
-        }
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ResizeAndPadImage",
+            category="image/transform",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Int.Input("target_width", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                IO.Int.Input("target_height", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                IO.Combo.Input("padding_color", options=["white", "black"]),
+                IO.Combo.Input("interpolation", options=["area", "bicubic", "nearest-exact", "bilinear", "lanczos"]),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "resize_and_pad"
-    CATEGORY = "image/transform"
-
-    def resize_and_pad(self, image, target_width, target_height, padding_color, interpolation):
+    @classmethod
+    def execute(cls, image, target_width, target_height, padding_color, interpolation) -> IO.NodeOutput:
         batch_size, orig_height, orig_width, channels = image.shape
 
         scale_w = target_width / orig_width
@@ -469,52 +414,47 @@ class ResizeAndPadImage:
         padded[:, :, y_offset:y_offset + new_height, x_offset:x_offset + new_width] = resized
 
         output = padded.permute(0, 2, 3, 1)
-        return (output,)
+        return IO.NodeOutput(output)
 
-class SaveSVGNode:
-    """
-    Save SVG files on disk.
-    """
+    resize_and_pad = execute  # TODO: remove
 
-    def __init__(self):
-        self.output_dir = folder_paths.get_output_directory()
-        self.type = "output"
-        self.prefix_append = ""
 
-    RETURN_TYPES = ()
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "save_svg"
-    CATEGORY = "image/save" # Changed
-    OUTPUT_NODE = True
+class SaveSVGNode(IO.ComfyNode):
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "svg": ("SVG",), # Changed
-                "filename_prefix": ("STRING", {"default": "svg/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": {
-                "prompt": "PROMPT",
-                "extra_pnginfo": "EXTRA_PNGINFO"
-            }
-        }
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="SaveSVGNode",
+            description="Save SVG files on disk.",
+            category="image/save",
+            inputs=[
+                IO.SVG.Input("svg"),
+                IO.String.Input(
+                    "filename_prefix",
+                    default="svg/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,
+        )
 
-    def save_svg(self, svg: SVG, filename_prefix="svg/ComfyUI", prompt=None, extra_pnginfo=None):
-        filename_prefix += self.prefix_append
-        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir)
-        results = list()
+    @classmethod
+    def execute(cls, svg: IO.SVG.Type, filename_prefix="svg/ComfyUI") -> IO.NodeOutput:
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, folder_paths.get_output_directory())
+        results: list[UI.SavedResult] = []
 
         # Prepare metadata JSON
         metadata_dict = {}
-        if prompt is not None:
-            metadata_dict["prompt"] = prompt
-        if extra_pnginfo is not None:
-            metadata_dict.update(extra_pnginfo)
+        if cls.hidden.prompt is not None:
+            metadata_dict["prompt"] = cls.hidden.prompt
+        if cls.hidden.extra_pnginfo is not None:
+            metadata_dict.update(cls.hidden.extra_pnginfo)
 
         # Convert metadata to JSON string
         metadata_json = json.dumps(metadata_dict, indent=2) if metadata_dict else None
 
+
         for batch_number, svg_bytes in enumerate(svg.data):
             filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
             file = f"{filename_with_batch_num}_{counter:05}_.svg"
@@ -544,57 +484,64 @@ class SaveSVGNode:
             with open(os.path.join(full_output_folder, file), 'wb') as svg_file:
                 svg_file.write(svg_content.encode('utf-8'))
 
-            results.append({
-                "filename": file,
-                "subfolder": subfolder,
-                "type": self.type
-            })
+            results.append(UI.SavedResult(filename=file, subfolder=subfolder, type=IO.FolderType.output))
             counter += 1
-        return { "ui": { "images": results } }
+        return IO.NodeOutput(ui={"images": results})
 
-class GetImageSize:
+    save_svg = execute  # TODO: remove
+
+
+class GetImageSize(IO.ComfyNode):
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": (IO.IMAGE,),
-            },
-            "hidden": {
-                "unique_id": "UNIQUE_ID",
-            }
-        }
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="GetImageSize",
+            display_name="Get Image Size",
+            description="Returns width and height of the image, and passes it through unchanged.",
+            category="image",
+            inputs=[
+                IO.Image.Input("image"),
+            ],
+            outputs=[
+                IO.Int.Output(display_name="width"),
+                IO.Int.Output(display_name="height"),
+                IO.Int.Output(display_name="batch_size"),
+            ],
+            hidden=[IO.Hidden.unique_id],
+        )
 
-    RETURN_TYPES = (IO.INT, IO.INT, IO.INT)
-    RETURN_NAMES = ("width", "height", "batch_size")
-    FUNCTION = "get_size"
-
-    CATEGORY = "image"
-    DESCRIPTION = """Returns width and height of the image, and passes it through unchanged."""
-
-    def get_size(self, image, unique_id=None) -> tuple[int, int]:
+    @classmethod
+    def execute(cls, image) -> IO.NodeOutput:
         height = image.shape[1]
         width = image.shape[2]
         batch_size = image.shape[0]
 
         # Send progress text to display size on the node
-        if unique_id:
-            PromptServer.instance.send_progress_text(f"width: {width}, height: {height}\n batch size: {batch_size}", unique_id)
+        if cls.hidden.unique_id:
+            PromptServer.instance.send_progress_text(f"width: {width}, height: {height}\n batch size: {batch_size}", cls.hidden.unique_id)
 
-        return width, height, batch_size
+        return IO.NodeOutput(width, height, batch_size)
+
+    get_size = execute  # TODO: remove
+
+
+class ImageRotate(IO.ComfyNode):
 
-class ImageRotate:
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": (IO.IMAGE,),
-                              "rotation": (["none", "90 degrees", "180 degrees", "270 degrees"],),
-                              }}
-    RETURN_TYPES = (IO.IMAGE,)
-    FUNCTION = "rotate"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageRotate",
+            category="image/transform",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Combo.Input("rotation", options=["none", "90 degrees", "180 degrees", "270 degrees"]),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/transform"
-
-    def rotate(self, image, rotation):
+    @classmethod
+    def execute(cls, image, rotation) -> IO.NodeOutput:
         rotate_by = 0
         if rotation.startswith("90"):
             rotate_by = 1
@@ -604,41 +551,57 @@ class ImageRotate:
             rotate_by = 3
 
         image = torch.rot90(image, k=rotate_by, dims=[2, 1])
-        return (image,)
+        return IO.NodeOutput(image)
+
+    rotate = execute  # TODO: remove
+
+
+class ImageFlip(IO.ComfyNode):
 
-class ImageFlip:
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": (IO.IMAGE,),
-                              "flip_method": (["x-axis: vertically", "y-axis: horizontally"],),
-                              }}
-    RETURN_TYPES = (IO.IMAGE,)
-    FUNCTION = "flip"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageFlip",
+            category="image/transform",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Combo.Input("flip_method", options=["x-axis: vertically", "y-axis: horizontally"]),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/transform"
-
-    def flip(self, image, flip_method):
+    @classmethod
+    def execute(cls, image, flip_method) -> IO.NodeOutput:
         if flip_method.startswith("x"):
             image = torch.flip(image, dims=[1])
         elif flip_method.startswith("y"):
             image = torch.flip(image, dims=[2])
 
-        return (image,)
+        return IO.NodeOutput(image)
 
-class ImageScaleToMaxDimension:
-    upscale_methods = ["area", "lanczos", "bilinear", "nearest-exact", "bilinear", "bicubic"]
+    flip = execute  # TODO: remove
+
+
+class ImageScaleToMaxDimension(IO.ComfyNode):
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"image": ("IMAGE",),
-                             "upscale_method": (s.upscale_methods,),
-                             "largest_size": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 1})}}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "upscale"
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageScaleToMaxDimension",
+            category="image/upscaling",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Combo.Input(
+                    "upscale_method",
+                    options=["area", "lanczos", "bilinear", "nearest-exact", "bilinear", "bicubic"],
+                ),
+                IO.Int.Input("largest_size", default=512, min=0, max=MAX_RESOLUTION, step=1),
+            ],
+            outputs=[IO.Image.Output()],
+        )
 
-    CATEGORY = "image/upscaling"
-
-    def upscale(self, image, upscale_method, largest_size):
+    @classmethod
+    def execute(cls, image, upscale_method, largest_size) -> IO.NodeOutput:
         height = image.shape[1]
         width = image.shape[2]
 
@@ -655,20 +618,30 @@ class ImageScaleToMaxDimension:
         samples = image.movedim(-1, 1)
         s = comfy.utils.common_upscale(samples, width, height, upscale_method, "disabled")
         s = s.movedim(1, -1)
-        return (s,)
+        return IO.NodeOutput(s)
 
-NODE_CLASS_MAPPINGS = {
-    "ImageCrop": ImageCrop,
-    "RepeatImageBatch": RepeatImageBatch,
-    "ImageFromBatch": ImageFromBatch,
-    "ImageAddNoise": ImageAddNoise,
-    "SaveAnimatedWEBP": SaveAnimatedWEBP,
-    "SaveAnimatedPNG": SaveAnimatedPNG,
-    "SaveSVGNode": SaveSVGNode,
-    "ImageStitch": ImageStitch,
-    "ResizeAndPadImage": ResizeAndPadImage,
-    "GetImageSize": GetImageSize,
-    "ImageRotate": ImageRotate,
-    "ImageFlip": ImageFlip,
-    "ImageScaleToMaxDimension": ImageScaleToMaxDimension,
-}
+    upscale = execute    # TODO: remove
+
+
+class ImagesExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[IO.ComfyNode]]:
+        return [
+            ImageCrop,
+            RepeatImageBatch,
+            ImageFromBatch,
+            ImageAddNoise,
+            SaveAnimatedWEBP,
+            SaveAnimatedPNG,
+            SaveSVGNode,
+            ImageStitch,
+            ResizeAndPadImage,
+            GetImageSize,
+            ImageRotate,
+            ImageFlip,
+            ImageScaleToMaxDimension,
+        ]
+
+
+async def comfy_entrypoint() -> ImagesExtension:
+    return ImagesExtension()

comfy_extras/nodes_logic.py

@@ -39,28 +39,6 @@ class SwitchNode(io.ComfyNode):
         return io.NodeOutput(on_true if switch else on_false)
 
 
-class MatchTypeTestNode(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        template = io.MatchType.Template("switch", [io.Image, io.Mask, io.Latent])
-        return io.Schema(
-            node_id="MatchTypeTestNode",
-            display_name="MatchTypeTest",
-            category="logic",
-            is_experimental=True,
-            inputs=[
-                io.MatchType.Input("input", template=template),
-            ],
-            outputs=[
-                io.MatchType.Output(template=template, display_name="output"),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, input) -> io.NodeOutput:
-        return io.NodeOutput(input)
-
-
 class SoftSwitchNode(io.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -131,6 +109,9 @@ class CustomComboNode(io.ComfyNode):
 
     @classmethod
     def validate_inputs(cls, choice: io.Combo.Type) -> bool:
+        # NOTE: DO NOT DO THIS unless you want to skip validation entirely on the node's inputs.
+        # I am doing that here because the widgets (besides the combo dropdown) on this node are fully frontend defined.
+        # I need to skip checking that the chosen combo option is in the options list, since those are defined by the user.
         return True
 
     @classmethod
@@ -253,21 +234,6 @@ class ConvertStringToComboNode(io.ComfyNode):
     def execute(cls, string: str) -> io.NodeOutput:
         return io.NodeOutput(string)
 
-class AnyTypeTestNode(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="AnyNodeTestNode",
-            display_name="AnyNodeTest",
-            category="logic",
-            inputs=[io.AnyType.Input("any")],
-            outputs=[io.AnyType.Output()],
-        )
-
-    @classmethod
-    def execute(cls, any: io.AnyType.Type) -> io.NodeOutput:
-        return io.NodeOutput(any)
-
 class InvertBooleanNode(io.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -288,16 +254,14 @@ class LogicExtension(ComfyExtension):
     async def get_node_list(self) -> list[type[io.ComfyNode]]:
         return [
             SwitchNode,
+            CustomComboNode,
             # SoftSwitchNode,
-            # CustomComboNode,
             # ConvertStringToComboNode,
             # DCTestNode,
             # AutogrowNamesTestNode,
             # AutogrowPrefixTestNode,
             # ComboOutputTestNode,
             # InvertBooleanNode,
-            # MatchTypeTestNode,
-            # AnyTypeTestNode,
         ]
 
 async def comfy_entrypoint() -> LogicExtension:

comfy_extras/nodes_post_processing.py

@@ -9,6 +9,7 @@ from typing import TypedDict, Literal
 
 import comfy.utils
 import comfy.model_management
+from comfy_extras.nodes_latent import reshape_latent_to
 import node_helpers
 from comfy_api.latest import ComfyExtension, io
 from nodes import MAX_RESOLUTION
@@ -443,6 +444,94 @@ class ResizeImageMaskNode(io.ComfyNode):
             return io.NodeOutput(scale_match_size(input, resize_type["match"], scale_method, resize_type["crop"]))
         raise ValueError(f"Unsupported resize type: {selected_type}")
 
+def batch_images(images: list[torch.Tensor]) -> torch.Tensor | None:
+    if len(images) == 0:
+        return None
+    # first, get the max channels count
+    max_channels = max(image.shape[-1] for image in images)
+    # then, pad all images to have the same channels count
+    padded_images: list[torch.Tensor] = []
+    for image in images:
+        if image.shape[-1] < max_channels:
+            padded_images.append(torch.nn.functional.pad(image, (0,1), mode='constant', value=1.0))
+        else:
+            padded_images.append(image)
+    # resize all images to be the same size as the first image
+    resized_images: list[torch.Tensor] = []
+    first_image_shape = padded_images[0].shape
+    for image in padded_images:
+        if image.shape[1:] != first_image_shape[1:]:
+            resized_images.append(comfy.utils.common_upscale(image.movedim(-1,1), first_image_shape[2], first_image_shape[1], "bilinear", "center").movedim(1,-1))
+        else:
+            resized_images.append(image)
+    # batch the images in the format [b, h, w, c]
+    return torch.cat(resized_images, dim=0)
+
+def batch_masks(masks: list[torch.Tensor]) -> torch.Tensor | None:
+    if len(masks) == 0:
+        return None
+    # resize all masks to be the same size as the first mask
+    resized_masks: list[torch.Tensor] = []
+    first_mask_shape = masks[0].shape
+    for mask in masks:
+        if mask.shape[1:] != first_mask_shape[1:]:
+            mask = init_image_mask_input(mask, is_type_image=False)
+            mask = comfy.utils.common_upscale(mask, first_mask_shape[2], first_mask_shape[1], "bilinear", "center")
+            resized_masks.append(finalize_image_mask_input(mask, is_type_image=False))
+        else:
+            resized_masks.append(mask)
+    # batch the masks in the format [b, h, w]
+    return torch.cat(resized_masks, dim=0)
+
+def batch_latents(latents: list[dict[str, torch.Tensor]]) -> dict[str, torch.Tensor] | None:
+    if len(latents) == 0:
+        return None
+    samples_out = latents[0].copy()
+    samples_out["batch_index"] = []
+    first_samples = latents[0]["samples"]
+    tensors: list[torch.Tensor] = []
+    for latent in latents:
+        # first, deal with latent tensors
+        tensors.append(reshape_latent_to(first_samples.shape, latent["samples"], repeat_batch=False))
+        # next, deal with batch_index
+        samples_out["batch_index"].extend(latent.get("batch_index", [x for x in range(0, latent["samples"].shape[0])]))
+    samples_out["samples"] = torch.cat(tensors, dim=0)
+    return samples_out
+
+class BatchImagesMasksLatentsNode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        matchtype_template = io.MatchType.Template("input", allowed_types=[io.Image, io.Mask, io.Latent])
+        autogrow_template = io.Autogrow.TemplatePrefix(
+                io.MatchType.Input("input", matchtype_template),
+                prefix="input", min=1, max=50)
+        return io.Schema(
+            node_id="BatchImagesMasksLatentsNode",
+            display_name="Batch Images/Masks/Latents",
+            category="util",
+            inputs=[
+                io.Autogrow.Input("inputs", template=autogrow_template)
+            ],
+            outputs=[
+                io.MatchType.Output(id=None, template=matchtype_template)
+            ]
+        )
+
+    @classmethod
+    def execute(cls, inputs: io.Autogrow.Type) -> io.NodeOutput:
+        batched = None
+        values = list(inputs.values())
+        # latents
+        if isinstance(values[0], dict):
+            batched = batch_latents(values)
+        # images
+        elif is_image(values[0]):
+            batched = batch_images(values)
+        # masks
+        else:
+            batched = batch_masks(values)
+        return io.NodeOutput(batched)
+
 class PostProcessingExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[io.ComfyNode]]:
@@ -453,6 +542,7 @@ class PostProcessingExtension(ComfyExtension):
             Sharpen,
             ImageScaleToTotalPixels,
             ResizeImageMaskNode,
+            # BatchImagesMasksLatentsNode,
         ]
 
 async def comfy_entrypoint() -> PostProcessingExtension:

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.5.1"
+__version__ = "0.6.0"

manager_requirements.txt

@@ -1 +1 @@
-comfyui_manager==4.0.3b7
+comfyui_manager==4.0.4

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.5.1"
+version = "0.6.0"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"

requirements.txt

@@ -1,5 +1,5 @@
-comfyui-frontend-package==1.34.9
-comfyui-workflow-templates==0.7.62
+comfyui-frontend-package==1.35.9
+comfyui-workflow-templates==0.7.64
 comfyui-embedded-docs==0.3.1
 torch
 torchsde

tests-unit/comfy_extras_test/image_stitch_test.py

@@ -25,7 +25,7 @@ class TestImageStitch:
 
         result = node.stitch(image1, "right", True, 0, "white", image2=None)
 
-        assert len(result) == 1
+        assert len(result.result) == 1
         assert torch.equal(result[0], image1)
 
     def test_basic_horizontal_stitch_right(self):