Merge branch 'v3-definition' into v3-definition-wip

comfy_api/v3/helpers.py

@@ -1,4 +1,4 @@
-from typing import Optional, Callable
+from typing import Callable, Optional
 
 
 def first_real_override(cls: type, name: str, *, base: type) -> Optional[Callable]:

comfy_api/v3/io.py

@@ -1,27 +1,30 @@
 from __future__ import annotations
-from typing import Any, Literal, TypeVar, Callable, TypedDict
+
-from typing_extensions import NotRequired
-from enum import Enum
-from abc import ABC, abstractmethod
-from dataclasses import dataclass, asdict
-from collections import Counter
-from comfy_execution.graph import ExecutionBlocker
-from comfy_api.internal import ComfyNodeInternal
-from comfy_api.v3.resources import Resources, ResourcesLocal
 import copy
+from abc import ABC, abstractmethod
+from collections import Counter
+from dataclasses import asdict, dataclass
+from enum import Enum
+from typing import Any, Callable, Literal, TypedDict, TypeVar
+
 # used for type hinting
 import torch
 from spandrel import ImageModelDescriptor
-from comfy.model_patcher import ModelPatcher
+from typing_extensions import NotRequired
-from comfy.samplers import Sampler, CFGGuider
+
-from comfy.sd import CLIP
-from comfy.controlnet import ControlNet
-from comfy.sd import VAE
-from comfy.sd import StyleModel as StyleModel_
 from comfy.clip_vision import ClipVisionModel
 from comfy.clip_vision import Output as ClipVisionOutput_
-from comfy_api.input import VideoInput
+from comfy.controlnet import ControlNet
 from comfy.hooks import HookGroup, HookKeyframeGroup
+from comfy.model_patcher import ModelPatcher
+from comfy.samplers import CFGGuider, Sampler
+from comfy.sd import CLIP, VAE
+from comfy.sd import StyleModel as StyleModel_
+from comfy_api.input import VideoInput
+from comfy_api.internal import ComfyNodeInternal
+from comfy_api.v3.resources import Resources, ResourcesLocal
+from comfy_execution.graph import ExecutionBlocker
+
 # from comfy_extras.nodes_images import SVG as SVG_ # NOTE: needs to be moved before can be imported due to circular reference
 
 
@@ -1191,7 +1194,7 @@ class ComfyNodeV3(ComfyNodeInternal):
 
     @classmethod
     def GET_NODE_INFO_V3(cls) -> dict[str, Any]:
-        schema = cls.GET_SCHEMA()
+        # schema = cls.GET_SCHEMA()
         # TODO: finish
         return None
 
@@ -1237,84 +1240,84 @@ class ComfyNodeV3(ComfyNodeInternal):
     #--------------------------------------------
     _DESCRIPTION = None
     @classproperty
-    def DESCRIPTION(cls):
+    def DESCRIPTION(cls):  # noqa
         if cls._DESCRIPTION is None:
             cls.GET_SCHEMA()
         return cls._DESCRIPTION
 
     _CATEGORY = None
     @classproperty
-    def CATEGORY(cls):
+    def CATEGORY(cls):  # noqa
         if cls._CATEGORY is None:
             cls.GET_SCHEMA()
         return cls._CATEGORY
 
     _EXPERIMENTAL = None
     @classproperty
-    def EXPERIMENTAL(cls):
+    def EXPERIMENTAL(cls):  # noqa
         if cls._EXPERIMENTAL is None:
             cls.GET_SCHEMA()
         return cls._EXPERIMENTAL
 
     _DEPRECATED = None
     @classproperty
-    def DEPRECATED(cls):
+    def DEPRECATED(cls):  # noqa
         if cls._DEPRECATED is None:
             cls.GET_SCHEMA()
         return cls._DEPRECATED
 
     _API_NODE = None
     @classproperty
-    def API_NODE(cls):
+    def API_NODE(cls):  # noqa
         if cls._API_NODE is None:
             cls.GET_SCHEMA()
         return cls._API_NODE
 
     _OUTPUT_NODE = None
     @classproperty
-    def OUTPUT_NODE(cls):
+    def OUTPUT_NODE(cls):  # noqa
         if cls._OUTPUT_NODE is None:
             cls.GET_SCHEMA()
         return cls._OUTPUT_NODE
 
     _INPUT_IS_LIST = None
     @classproperty
-    def INPUT_IS_LIST(cls):
+    def INPUT_IS_LIST(cls):  # noqa
         if cls._INPUT_IS_LIST is None:
             cls.GET_SCHEMA()
         return cls._INPUT_IS_LIST
     _OUTPUT_IS_LIST = None
 
     @classproperty
-    def OUTPUT_IS_LIST(cls):
+    def OUTPUT_IS_LIST(cls):  # noqa
         if cls._OUTPUT_IS_LIST is None:
             cls.GET_SCHEMA()
         return cls._OUTPUT_IS_LIST
 
     _RETURN_TYPES = None
     @classproperty
-    def RETURN_TYPES(cls):
+    def RETURN_TYPES(cls):  # noqa
         if cls._RETURN_TYPES is None:
             cls.GET_SCHEMA()
         return cls._RETURN_TYPES
 
     _RETURN_NAMES = None
     @classproperty
-    def RETURN_NAMES(cls):
+    def RETURN_NAMES(cls):  # noqa
         if cls._RETURN_NAMES is None:
             cls.GET_SCHEMA()
         return cls._RETURN_NAMES
 
     _OUTPUT_TOOLTIPS = None
     @classproperty
-    def OUTPUT_TOOLTIPS(cls):
+    def OUTPUT_TOOLTIPS(cls):  # noqa
         if cls._OUTPUT_TOOLTIPS is None:
             cls.GET_SCHEMA()
         return cls._OUTPUT_TOOLTIPS
 
     _NOT_IDEMPOTENT = None
     @classproperty
-    def NOT_IDEMPOTENT(cls):
+    def NOT_IDEMPOTENT(cls):  # noqa
         if cls._NOT_IDEMPOTENT is None:
             cls.GET_SCHEMA()
         return cls._NOT_IDEMPOTENT
@@ -1494,36 +1497,36 @@ class TestNode(ComfyNodeV3):
     def execute(cls, **kwargs):
         pass
 
-if __name__ == "__main__":
+# if __name__ == "__main__":
-    print("hello there")
+#     print("hello there")
-    inputs: list[InputV3] = [
+#     inputs: list[InputV3] = [
-        Int.Input("tessfes", widgetType=String.io_type),
+#         Int.Input("tessfes", widgetType=String.io_type),
-        Int.Input("my_int"),
+#         Int.Input("my_int"),
-        Custom("XYZ").Input("xyz"),
+#         Custom("XYZ").Input("xyz"),
-        Custom("MODEL_M").Input("model1"),
+#         Custom("MODEL_M").Input("model1"),
-        Image.Input("my_image"),
+#         Image.Input("my_image"),
-        Float.Input("my_float"),
+#         Float.Input("my_float"),
-        MultiType.Input("my_inputs", [String, Custom("MODEL_M"), Custom("XYZ")]),
+#         MultiType.Input("my_inputs", [String, Custom("MODEL_M"), Custom("XYZ")]),
-    ]
+#     ]
-    Custom("XYZ").Input()
+#     Custom("XYZ").Input()
-    outputs: list[OutputV3] = [
+#     outputs: list[OutputV3] = [
-        Image.Output("image"),
+#         Image.Output("image"),
-        Custom("XYZ").Output("xyz"),
+#         Custom("XYZ").Output("xyz"),
-    ]
+#     ]
-
+#
-    for c in inputs:
+#     for c in inputs:
-        if isinstance(c, MultiType):
+#         if isinstance(c, MultiType):
-            print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}, {[x.io_type for x in c.io_types]}")
+#             print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}, {[x.io_type for x in c.io_types]}")
-            print(c.get_io_type_V1())
+#             print(c.get_io_type_V1())
-        else:
+#         else:
-            print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}")
+#             print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}")
-
+#
-    for c in outputs:
+#     for c in outputs:
-        print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}")
+#         print(f"{c}, {type(c)}, {type(c).io_type}, {c.id}")
-
+#
-    zz = TestNode()
+#     zz = TestNode()
-    print(zz.GET_NODE_INFO_V1())
+#     print(zz.GET_NODE_INFO_V1())
-
+#
-    # aa = NodeInfoV1()
+#     # aa = NodeInfoV1()
-    # print(asdict(aa))
+#     # print(asdict(aa))
-    # print(as_pruned_dict(aa))
+#     # print(as_pruned_dict(aa))

comfy_api/v3/ui.py

@@ -1,15 +1,21 @@
 from __future__ import annotations
 
-from comfy_api.v3.io import Image, FolderType, _UIOutput, ComfyNodeV3
+import json
-# used for image preview
+import os
-from comfy.cli_args import args
-import folder_paths
 import random
+from io import BytesIO
+
+import av
+import numpy as np
+import torchaudio
 from PIL import Image as PILImage
 from PIL.PngImagePlugin import PngInfo
-import os
+
-import json
+import folder_paths
-import numpy as np
+
+# used for image preview
+from comfy.cli_args import args
+from comfy_api.v3.io import ComfyNodeV3, FolderType, Image, _UIOutput
 
 
 class SavedResult(dict):
@@ -63,11 +69,13 @@ class PreviewImage(_UIOutput):
             "animated": (self.animated,)
         }
 
+
 class PreviewMask(PreviewImage):
     def __init__(self, mask: PreviewMask.Type, animated: bool=False, cls: ComfyNodeV3=None, **kwargs):
         preview = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)
         super().__init__(preview, animated, cls, **kwargs)
 
+
 # class UILatent(_UIOutput):
 #     def __init__(self, values: list[SavedResult | dict], **kwargs):
 #         output_dir = folder_paths.get_temp_directory()
@@ -115,13 +123,113 @@ class PreviewMask(PreviewImage):
 #             "latents": self.values,
 #         }
 
+
 class PreviewAudio(_UIOutput):
-    def __init__(self, values: list[SavedResult | dict], **kwargs):
+    def __init__(self, audio, cls: ComfyNodeV3=None, **kwargs):
-        self.values = values
+        quality = "128k"
+        format = "flac"
+
+        filename_prefix = "ComfyUI_temp_" + ''.join(random.choice("abcdefghijklmnopqrstupvxyz") for x in range(5))
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
+            filename_prefix, folder_paths.get_temp_directory()
+        )
+
+        # Prepare metadata dictionary
+        metadata = {}
+        if not args.disable_metadata and cls is not None:
+            if cls.hidden.prompt is not None:
+                metadata["prompt"] = json.dumps(cls.hidden.prompt)
+            if cls.hidden.extra_pnginfo is not None:
+                for x in cls.hidden.extra_pnginfo:
+                    metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+        # Opus supported sample rates
+        OPUS_RATES = [8000, 12000, 16000, 24000, 48000]
+        results = []
+        for (batch_number, waveform) in enumerate(audio["waveform"].cpu()):
+            filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
+            file = f"{filename_with_batch_num}_{counter:05}_.{format}"
+            output_path = os.path.join(full_output_folder, file)
+
+            # Use original sample rate initially
+            sample_rate = audio["sample_rate"]
+
+            # Handle Opus sample rate requirements
+            if format == "opus":
+                if sample_rate > 48000:
+                    sample_rate = 48000
+                elif sample_rate not in OPUS_RATES:
+                    # Find the next highest supported rate
+                    for rate in sorted(OPUS_RATES):
+                        if rate > sample_rate:
+                            sample_rate = rate
+                            break
+                    if sample_rate not in OPUS_RATES:  # Fallback if still not supported
+                        sample_rate = 48000
+
+                # Resample if necessary
+                if sample_rate != audio["sample_rate"]:
+                    waveform = torchaudio.functional.resample(waveform, audio["sample_rate"], sample_rate)
+
+            # Create output with specified format
+            output_buffer = BytesIO()
+            output_container = av.open(output_buffer, mode='w', format=format)
+
+            # Set metadata on the container
+            for key, value in metadata.items():
+                output_container.metadata[key] = value
+
+            # Set up the output stream with appropriate properties
+            if format == "opus":
+                out_stream = output_container.add_stream("libopus", rate=sample_rate)
+                if quality == "64k":
+                    out_stream.bit_rate = 64000
+                elif quality == "96k":
+                    out_stream.bit_rate = 96000
+                elif quality == "128k":
+                    out_stream.bit_rate = 128000
+                elif quality == "192k":
+                    out_stream.bit_rate = 192000
+                elif quality == "320k":
+                    out_stream.bit_rate = 320000
+            elif format == "mp3":
+                out_stream = output_container.add_stream("libmp3lame", rate=sample_rate)
+                if quality == "V0":
+                    # TODO i would really love to support V3 and V5 but there doesn't seem to be a way to set the qscale level, the property below is a bool
+                    out_stream.codec_context.qscale = 1
+                elif quality == "128k":
+                    out_stream.bit_rate = 128000
+                elif quality == "320k":
+                    out_stream.bit_rate = 320000
+            else:  # format == "flac":
+                out_stream = output_container.add_stream("flac", rate=sample_rate)
+
+            frame = av.AudioFrame.from_ndarray(waveform.movedim(0, 1).reshape(1, -1).float().numpy(), format='flt',
+                                               layout='mono' if waveform.shape[0] == 1 else 'stereo')
+            frame.sample_rate = sample_rate
+            frame.pts = 0
+            output_container.mux(out_stream.encode(frame))
+
+            # Flush encoder
+            output_container.mux(out_stream.encode(None))
+
+            # Close containers
+            output_container.close()
+
+            # Write the output to file
+            output_buffer.seek(0)
+            with open(output_path, 'wb') as f:
+                f.write(output_buffer.getbuffer())
+
+            results.append(SavedResult(file, subfolder, FolderType.temp))
+            counter += 1
+
+        self.values = results
 
     def as_dict(self):
         return {"audio": self.values}
 
+
 class PreviewUI3D(_UIOutput):
     def __init__(self, values: list[SavedResult | dict], **kwargs):
         self.values = values
@@ -129,6 +237,7 @@ class PreviewUI3D(_UIOutput):
     def as_dict(self):
         return {"3d": self.values}
 
+
 class PreviewText(_UIOutput):
     def __init__(self, value: str, **kwargs):
         self.value = value

comfy_extras/v3/nodes_audio.py

@@ -0,0 +1,347 @@
+from __future__ import annotations
+
+import hashlib
+import json
+import os
+from io import BytesIO
+
+import av
+import torch
+import torchaudio
+
+import comfy.model_management
+import folder_paths
+import node_helpers
+from comfy.cli_args import args
+from comfy_api.v3 import io, ui
+
+
+class ConditioningStableAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="ConditioningStableAudio_V3",
+            category="conditioning",
+            inputs=[
+                io.Conditioning.Input(id="positive"),
+                io.Conditioning.Input(id="negative"),
+                io.Float.Input(id="seconds_start", default=0.0, min=0.0, max=1000.0, step=0.1),
+                io.Float.Input(id="seconds_total", default=47.0, min=0.0, max=1000.0, step=0.1),
+            ],
+            outputs=[
+                io.Conditioning.Output(id="positive_out", display_name="positive"),
+                io.Conditioning.Output(id="negative_out", display_name="negative"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, seconds_start, seconds_total) -> io.NodeOutput:
+        return io.NodeOutput(
+            node_helpers.conditioning_set_values(
+                positive, {"seconds_start": seconds_start, "seconds_total": seconds_total}
+            ),
+            node_helpers.conditioning_set_values(
+                negative, {"seconds_start": seconds_start, "seconds_total": seconds_total}
+            ),
+        )
+
+
+class EmptyLatentAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="EmptyLatentAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Float.Input(id="seconds", default=47.6, min=1.0, max=1000.0, step=0.1),
+                io.Int.Input(
+                    id="batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
+                ),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, seconds, batch_size) -> io.NodeOutput:
+        length = round((seconds * 44100 / 2048) / 2) * 2
+        latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device())
+        return io.NodeOutput({"samples": latent, "type": "audio"})
+
+
+class LoadAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="LoadAudio_V3",  # frontend expects "LoadAudio" to work
+            display_name="Load Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Combo.Input("audio", upload=io.UploadType.audio, options=cls.get_files_options()),
+            ],
+            outputs=[io.Audio.Output()],
+        )
+
+    @classmethod
+    def get_files_options(cls) -> list[str]:
+        input_dir = folder_paths.get_input_directory()
+        return sorted(folder_paths.filter_files_content_types(os.listdir(input_dir), ["audio", "video"]))
+
+    @classmethod
+    def execute(cls, audio) -> io.NodeOutput:
+        waveform, sample_rate = torchaudio.load(folder_paths.get_annotated_filepath(audio))
+        return io.NodeOutput({"waveform": waveform.unsqueeze(0), "sample_rate": sample_rate})
+
+    @classmethod
+    def fingerprint_inputs(s, audio):
+        image_path = folder_paths.get_annotated_filepath(audio)
+        m = hashlib.sha256()
+        with open(image_path, "rb") as f:
+            m.update(f.read())
+        return m.digest().hex()
+
+    @classmethod
+    def validate_inputs(s, audio):
+        if not folder_paths.exists_annotated_filepath(audio):
+            return "Invalid audio file: {}".format(audio)
+        return True
+
+
+class PreviewAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PreviewAudio_V3",  # frontend expects "PreviewAudio" to work
+            display_name="Preview Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio) -> io.NodeOutput:
+        return io.NodeOutput(ui=ui.PreviewAudio(audio, cls=cls))
+
+
+class SaveAudioMP3_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="SaveAudioMP3_V3",  # frontend expects "SaveAudioMP3" to work
+            display_name="Save Audio(MP3) _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+                io.Combo.Input("quality", options=["V0", "128k", "320k"], default="V0"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(self, audio, filename_prefix="ComfyUI", format="mp3", quality="V0") -> io.NodeOutput:
+        return _save_audio(self, audio, filename_prefix, format, quality)
+
+
+class SaveAudioOpus_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="SaveAudioOpus_V3",  # frontend expects "SaveAudioOpus" to work
+            display_name="Save Audio(Opus) _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+                io.Combo.Input("quality", options=["64k", "96k", "128k", "192k", "320k"], default="128k"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(self, audio, filename_prefix="ComfyUI", format="opus", quality="128k") -> io.NodeOutput:
+        return _save_audio(self, audio, filename_prefix, format, quality)
+
+
+class SaveAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="SaveAudio_V3",  # frontend expects "SaveAudio" to work
+            display_name="Save Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio, filename_prefix="ComfyUI", format="flac") -> io.NodeOutput:
+        return _save_audio(cls, audio, filename_prefix, format)
+
+
+class VAEDecodeAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="VAEDecodeAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Latent.Input(id="samples"),
+                io.Vae.Input(id="vae"),
+            ],
+            outputs=[io.Audio.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, samples) -> io.NodeOutput:
+        audio = vae.decode(samples["samples"]).movedim(-1, 1)
+        std = torch.std(audio, dim=[1, 2], keepdim=True) * 5.0
+        std[std < 1.0] = 1.0
+        audio /= std
+        return io.NodeOutput({"waveform": audio, "sample_rate": 44100})
+
+
+class VAEEncodeAudio_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="VAEEncodeAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Audio.Input(id="audio"),
+                io.Vae.Input(id="vae"),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, audio) -> io.NodeOutput:
+        sample_rate = audio["sample_rate"]
+        if 44100 != sample_rate:
+            waveform = torchaudio.functional.resample(audio["waveform"], sample_rate, 44100)
+        else:
+            waveform = audio["waveform"]
+        return io.NodeOutput({"samples": vae.encode(waveform.movedim(1, -1))})
+
+
+def _save_audio(cls, audio, filename_prefix="ComfyUI", format="flac", quality="128k") -> io.NodeOutput:
+    full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
+        filename_prefix, folder_paths.get_output_directory()
+    )
+
+    # Prepare metadata dictionary
+    metadata = {}
+    if not args.disable_metadata:
+        if cls.hidden.prompt is not None:
+            metadata["prompt"] = json.dumps(cls.hidden.prompt)
+        if cls.hidden.extra_pnginfo is not None:
+            for x in cls.hidden.extra_pnginfo:
+                metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+    # Opus supported sample rates
+    OPUS_RATES = [8000, 12000, 16000, 24000, 48000]
+
+    results = []
+    for batch_number, waveform in enumerate(audio["waveform"].cpu()):
+        filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
+        file = f"{filename_with_batch_num}_{counter:05}_.{format}"
+        output_path = os.path.join(full_output_folder, file)
+
+        # Use original sample rate initially
+        sample_rate = audio["sample_rate"]
+
+        # Handle Opus sample rate requirements
+        if format == "opus":
+            if sample_rate > 48000:
+                sample_rate = 48000
+            elif sample_rate not in OPUS_RATES:
+                # Find the next highest supported rate
+                for rate in sorted(OPUS_RATES):
+                    if rate > sample_rate:
+                        sample_rate = rate
+                        break
+                if sample_rate not in OPUS_RATES:  # Fallback if still not supported
+                    sample_rate = 48000
+
+            # Resample if necessary
+            if sample_rate != audio["sample_rate"]:
+                waveform = torchaudio.functional.resample(waveform, audio["sample_rate"], sample_rate)
+
+        # Create output with specified format
+        output_buffer = BytesIO()
+        output_container = av.open(output_buffer, mode="w", format=format)
+
+        # Set metadata on the container
+        for key, value in metadata.items():
+            output_container.metadata[key] = value
+
+        # Set up the output stream with appropriate properties
+        if format == "opus":
+            out_stream = output_container.add_stream("libopus", rate=sample_rate)
+            if quality == "64k":
+                out_stream.bit_rate = 64000
+            elif quality == "96k":
+                out_stream.bit_rate = 96000
+            elif quality == "128k":
+                out_stream.bit_rate = 128000
+            elif quality == "192k":
+                out_stream.bit_rate = 192000
+            elif quality == "320k":
+                out_stream.bit_rate = 320000
+        elif format == "mp3":
+            out_stream = output_container.add_stream("libmp3lame", rate=sample_rate)
+            if quality == "V0":
+                # TODO i would really love to support V3 and V5 but there doesn't seem to be a way to set the qscale level, the property below is a bool
+                out_stream.codec_context.qscale = 1
+            elif quality == "128k":
+                out_stream.bit_rate = 128000
+            elif quality == "320k":
+                out_stream.bit_rate = 320000
+        else:  # format == "flac":
+            out_stream = output_container.add_stream("flac", rate=sample_rate)
+
+        frame = av.AudioFrame.from_ndarray(
+            waveform.movedim(0, 1).reshape(1, -1).float().numpy(),
+            format="flt",
+            layout="mono" if waveform.shape[0] == 1 else "stereo",
+        )
+        frame.sample_rate = sample_rate
+        frame.pts = 0
+        output_container.mux(out_stream.encode(frame))
+
+        # Flush encoder
+        output_container.mux(out_stream.encode(None))
+
+        # Close containers
+        output_container.close()
+
+        # Write the output to file
+        output_buffer.seek(0)
+        with open(output_path, "wb") as f:
+            f.write(output_buffer.getbuffer())
+
+        results.append(ui.SavedResult(file, subfolder, io.FolderType.output))
+        counter += 1
+
+    return io.NodeOutput(ui={"audio": results})
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [
+    ConditioningStableAudio_V3,
+    EmptyLatentAudio_V3,
+    LoadAudio_V3,
+    PreviewAudio_V3,
+    SaveAudioMP3_V3,
+    SaveAudioOpus_V3,
+    SaveAudio_V3,
+    VAEDecodeAudio_V3,
+    VAEEncodeAudio_V3,
+]

comfy_extras/v3/nodes_controlnet.py

@@ -1,5 +1,5 @@
-from comfy.cldm.control_types import UNION_CONTROLNET_TYPES
 import comfy.utils
+from comfy.cldm.control_types import UNION_CONTROLNET_TYPES
 from comfy_api.v3 import io
 
 
@@ -27,11 +27,13 @@ class ControlNetApplyAdvanced_V3(io.ComfyNodeV3):
         )
 
     @classmethod
-    def execute(cls, positive, negative, control_net, image, strength, start_percent, end_percent, vae=None, extra_concat=[]) -> io.NodeOutput:
+    def execute(
+        cls, positive, negative, control_net, image, strength, start_percent, end_percent, vae=None, extra_concat=[]
+    ) -> io.NodeOutput:
         if strength == 0:
             return io.NodeOutput(positive, negative)
 
-        control_hint = image.movedim(-1,1)
+        control_hint = image.movedim(-1, 1)
         cnets = {}
 
         out = []
@@ -40,16 +42,18 @@ class ControlNetApplyAdvanced_V3(io.ComfyNodeV3):
             for t in conditioning:
                 d = t[1].copy()
 
-                prev_cnet = d.get('control', None)
+                prev_cnet = d.get("control", None)
                 if prev_cnet in cnets:
                     c_net = cnets[prev_cnet]
                 else:
-                    c_net = control_net.copy().set_cond_hint(control_hint, strength, (start_percent, end_percent), vae=vae, extra_concat=extra_concat)
+                    c_net = control_net.copy().set_cond_hint(
+                        control_hint, strength, (start_percent, end_percent), vae=vae, extra_concat=extra_concat
+                    )
                     c_net.set_previous_controlnet(prev_cnet)
                     cnets[prev_cnet] = c_net
 
-                d['control'] = c_net
+                d["control"] = c_net
-                d['control_apply_to_uncond'] = False
+                d["control_apply_to_uncond"] = False
                 n = [t[0], d]
                 c.append(n)
             out.append(c)
@@ -107,7 +111,9 @@ class ControlNetInpaintingAliMamaApply_V3(ControlNetApplyAdvanced_V3):
         )
 
     @classmethod
-    def execute(cls, positive, negative, control_net, vae, image, mask, strength, start_percent, end_percent) -> io.NodeOutput:
+    def execute(
+        cls, positive, negative, control_net, vae, image, mask, strength, start_percent, end_percent
+    ) -> io.NodeOutput:
         extra_concat = []
         if control_net.concat_mask:
             mask = 1.0 - mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1]))
@@ -115,7 +121,17 @@ class ControlNetInpaintingAliMamaApply_V3(ControlNetApplyAdvanced_V3):
             image = image * mask_apply.movedim(1, -1).repeat(1, 1, 1, image.shape[3])
             extra_concat = [mask]
 
-        return super().execute(positive, negative, control_net, image, strength, start_percent, end_percent, vae=vae, extra_concat=extra_concat)
+        return super().execute(
+            positive,
+            negative,
+            control_net,
+            image,
+            strength,
+            start_percent,
+            end_percent,
+            vae=vae,
+            extra_concat=extra_concat,
+        )
 
 
 NODES_LIST: list[type[io.ComfyNodeV3]] = [

comfy_extras/v3/nodes_images.py

@@ -1,16 +1,16 @@
+import hashlib
 import json
 import os
-import torch
-import hashlib
 
 import numpy as np
+import torch
 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
+from comfy.cli_args import args
+from comfy_api.v3 import io, ui
 
 
 class SaveImage_V3(io.ComfyNodeV3):
@@ -29,7 +29,8 @@ class SaveImage_V3(io.ComfyNodeV3):
                 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.",
+                    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],
@@ -42,8 +43,8 @@ class SaveImage_V3(io.ComfyNodeV3):
             filename_prefix, folder_paths.get_output_directory(), images[0].shape[1], images[0].shape[0]
         )
         results = []
-        for (batch_number, image) in enumerate(images):
+        for batch_number, image in enumerate(images):
-            i = 255. * image.cpu().numpy()
+            i = 255.0 * image.cpu().numpy()
             img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
             metadata = None
             if not args.disable_metadata:
@@ -82,13 +83,13 @@ class SaveAnimatedPNG_V3(io.ComfyNodeV3):
 
     @classmethod
     def execute(cls, images, fps, compress_level, filename_prefix="ComfyUI") -> io.NodeOutput:
-        full_output_folder, filename, counter, subfolder, filename_prefix = (
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
-            folder_paths.get_save_image_path(filename_prefix, folder_paths.get_output_directory(), images[0].shape[1], images[0].shape[0])
+            filename_prefix, folder_paths.get_output_directory(), images[0].shape[1], images[0].shape[0]
         )
         results = []
         pil_images = []
         for image in images:
-            img = Image.fromarray(np.clip(255. * image.cpu().numpy(), 0, 255).astype(np.uint8))
+            img = Image.fromarray(np.clip(255.0 * image.cpu().numpy(), 0, 255).astype(np.uint8))
             pil_images.append(img)
 
         metadata = None
@@ -96,19 +97,34 @@ class SaveAnimatedPNG_V3(io.ComfyNodeV3):
             metadata = PngInfo()
             if cls.hidden.prompt is not None:
                 metadata.add(
-                    b"comf", "prompt".encode("latin-1", "strict") + b"\0" + json.dumps(cls.hidden.prompt).encode("latin-1", "strict"), after_idat=True
+                    b"comf",
+                    "prompt".encode("latin-1", "strict")
+                    + b"\0"
+                    + json.dumps(cls.hidden.prompt).encode("latin-1", "strict"),
+                    after_idat=True,
                 )
             if cls.hidden.extra_pnginfo is not None:
                 for x in cls.hidden.extra_pnginfo:
                     metadata.add(
-                        b"comf", x.encode("latin-1", "strict") + b"\0" + json.dumps(cls.hidden.extra_pnginfo[x]).encode("latin-1", "strict"), after_idat=True
+                        b"comf",
+                        x.encode("latin-1", "strict")
+                        + b"\0"
+                        + json.dumps(cls.hidden.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:])
+        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(ui.SavedResult(file, subfolder, io.FolderType.output))
 
-        return io.NodeOutput(ui={"images": results, "animated": (True,) })
+        return io.NodeOutput(ui={"images": results, "animated": (True,)})
 
 
 class SaveAnimatedWEBP_V3(io.ComfyNodeV3):
@@ -136,11 +152,13 @@ class SaveAnimatedWEBP_V3(io.ComfyNodeV3):
     @classmethod
     def execute(cls, images, fps, filename_prefix, lossless, quality, method, num_frames=0) -> io.NodeOutput:
         method = cls.COMPRESS_METHODS.get(method)
-        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])
+        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 = []
         pil_images = []
         for image in images:
-            img = Image.fromarray(np.clip(255. * image.cpu().numpy(), 0, 255).astype(np.uint8))
+            img = Image.fromarray(np.clip(255.0 * image.cpu().numpy(), 0, 255).astype(np.uint8))
             pil_images.append(img)
 
         metadata = pil_images[0].getexif()
@@ -148,7 +166,7 @@ class SaveAnimatedWEBP_V3(io.ComfyNodeV3):
             if cls.hidden.prompt is not None:
                 metadata[0x0110] = "prompt:{}".format(json.dumps(cls.hidden.prompt))
             if cls.hidden.extra_pnginfo is not None:
-                inital_exif = 0x010f
+                inital_exif = 0x010F
                 for x in cls.hidden.extra_pnginfo:
                     metadata[inital_exif] = "{}:{}".format(x, json.dumps(cls.hidden.extra_pnginfo[x]))
                     inital_exif -= 1
@@ -160,8 +178,9 @@ class SaveAnimatedWEBP_V3(io.ComfyNodeV3):
             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),
+                save_all=True,
-                append_images=pil_images[i + 1:i + num_frames],
+                duration=int(1000.0 / fps),
+                append_images=pil_images[i + 1 : i + num_frames],
                 exif=metadata,
                 lossless=lossless,
                 quality=quality,
@@ -228,12 +247,12 @@ class LoadImage_V3(io.ComfyNodeV3):
         output_masks = []
         w, h = None, None
 
-        excluded_formats = ['MPO']
+        excluded_formats = ["MPO"]
 
         for i in ImageSequence.Iterator(img):
             i = node_helpers.pillow(ImageOps.exif_transpose, i)
 
-            if i.mode == 'I':
+            if i.mode == "I":
                 i = i.point(lambda i: i * (1 / 255))
             image = i.convert("RGB")
 
@@ -246,14 +265,14 @@ class LoadImage_V3(io.ComfyNodeV3):
 
             image = np.array(image).astype(np.float32) / 255.0
             image = torch.from_numpy(image)[None,]
-            if 'A' in i.getbands():
+            if "A" in i.getbands():
-                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
-            elif i.mode == 'P' and 'transparency' in i.info:
+            elif i.mode == "P" and "transparency" in i.info:
-                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.convert("RGBA").getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
             else:
-                mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
+                mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
             output_images.append(image)
             output_masks.append(mask.unsqueeze(0))
 
@@ -270,7 +289,7 @@ class LoadImage_V3(io.ComfyNodeV3):
     def fingerprint_inputs(s, image):
         image_path = folder_paths.get_annotated_filepath(image)
         m = hashlib.sha256()
-        with open(image_path, 'rb') as f:
+        with open(image_path, "rb") as f:
             m.update(f.read())
         return m.digest().hex()
 
@@ -288,8 +307,8 @@ class LoadImageOutput_V3(io.ComfyNodeV3):
             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 "
+            "When the refresh button is clicked, the node will update the image list "
-                        "and automatically select the first image, allowing for easy iteration.",
+            "and automatically select the first image, allowing for easy iteration.",
             category="image",
             inputs=[
                 io.Combo.Input(
@@ -317,12 +336,12 @@ class LoadImageOutput_V3(io.ComfyNodeV3):
         output_masks = []
         w, h = None, None
 
-        excluded_formats = ['MPO']
+        excluded_formats = ["MPO"]
 
         for i in ImageSequence.Iterator(img):
             i = node_helpers.pillow(ImageOps.exif_transpose, i)
 
-            if i.mode == 'I':
+            if i.mode == "I":
                 i = i.point(lambda i: i * (1 / 255))
             image = i.convert("RGB")
 
@@ -335,12 +354,12 @@ class LoadImageOutput_V3(io.ComfyNodeV3):
 
             image = np.array(image).astype(np.float32) / 255.0
             image = torch.from_numpy(image)[None,]
-            if 'A' in i.getbands():
+            if "A" in i.getbands():
-                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
-            elif i.mode == 'P' and 'transparency' in i.info:
+            elif i.mode == "P" and "transparency" in i.info:
-                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.convert("RGBA").getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
             else:
                 mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
             output_images.append(image)
@@ -359,7 +378,7 @@ class LoadImageOutput_V3(io.ComfyNodeV3):
     def fingerprint_inputs(s, image):
         image_path = folder_paths.get_annotated_filepath(image)
         m = hashlib.sha256()
-        with open(image_path, 'rb') as f:
+        with open(image_path, "rb") as f:
             m.update(f.read())
         return m.digest().hex()
 

comfy_extras/v3/nodes_primitive.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+
+import sys
+
+from comfy_api.v3 import io
+
+
+class String_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PrimitiveString_V3",
+            display_name="String _V3",
+            category="utils/primitive",
+            inputs=[
+                io.String.Input("value"),
+            ],
+            outputs=[io.String.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: str) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class StringMultiline_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PrimitiveStringMultiline_V3",
+            display_name="String (Multiline) _V3",
+            category="utils/primitive",
+            inputs=[
+                io.String.Input("value", multiline=True),
+            ],
+            outputs=[io.String.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: str) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Int_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PrimitiveInt_V3",
+            display_name="Int _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Int.Input("value", min=-sys.maxsize, max=sys.maxsize, control_after_generate=True),
+            ],
+            outputs=[io.Int.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: int) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Float_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PrimitiveFloat_V3",
+            display_name="Float _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Float.Input("value", min=-sys.maxsize, max=sys.maxsize),
+            ],
+            outputs=[io.Float.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: float) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Boolean_V3(io.ComfyNodeV3):
+    @classmethod
+    def DEFINE_SCHEMA(cls):
+        return io.SchemaV3(
+            node_id="PrimitiveBoolean_V3",
+            display_name="Boolean _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Boolean.Input("value"),
+            ],
+            outputs=[io.Boolean.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: bool) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [
+    String_V3,
+    StringMultiline_V3,
+    Int_V3,
+    Float_V3,
+    Boolean_V3,
+]

comfy_extras/v3/nodes_stable_cascade.py

@@ -1,25 +1,25 @@
 """
-    This file is part of ComfyUI.
+This file is part of ComfyUI.
-    Copyright (C) 2024 Stability AI
+Copyright (C) 2024 Stability AI
 
-    This program is free software: you can redistribute it and/or modify
+This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
+it under the terms of the GNU General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
+the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
+(at your option) any later version.
 
-    This program is distributed in the hope that it will be useful,
+This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
+but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
+GNU General Public License for more details.
 
-    You should have received a copy of the GNU General Public License
+You should have received a copy of the GNU General Public License
-    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
 
 import torch
-import nodes
-import comfy.utils
 
+import comfy.utils
+import nodes
 from comfy_api.v3 import io
 
 
@@ -30,7 +30,7 @@ class StableCascade_EmptyLatentImage_V3(io.ComfyNodeV3):
             node_id="StableCascade_EmptyLatentImage_V3",
             category="latent/stable_cascade",
             inputs=[
-                io.Int.Input("width", default=1024,min=256,max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("width", default=1024, min=256, max=nodes.MAX_RESOLUTION, step=8),
                 io.Int.Input("height", default=1024, min=256, max=nodes.MAX_RESOLUTION, step=8),
                 io.Int.Input("compression", default=42, min=4, max=128, step=1),
                 io.Int.Input("batch_size", default=1, min=1, max=4096),
@@ -72,9 +72,9 @@ class StableCascade_StageC_VAEEncode_V3(io.ComfyNodeV3):
         out_width = (width // compression) * vae.downscale_ratio
         out_height = (height // compression) * vae.downscale_ratio
 
-        s = comfy.utils.common_upscale(image.movedim(-1,1), out_width, out_height, "bicubic", "center").movedim(1,-1)
+        s = comfy.utils.common_upscale(image.movedim(-1, 1), out_width, out_height, "bicubic", "center").movedim(1, -1)
 
-        c_latent = vae.encode(s[:,:,:,:3])
+        c_latent = vae.encode(s[:, :, :, :3])
         b_latent = torch.zeros([c_latent.shape[0], 4, (height // 8) * 2, (width // 8) * 2])
         return io.NodeOutput({"samples": c_latent}, {"samples": b_latent})
 
@@ -90,7 +90,7 @@ class StableCascade_StageB_Conditioning_V3(io.ComfyNodeV3):
                 io.Latent.Input("stage_c"),
             ],
             outputs=[
-              io.Conditioning.Output(),
+                io.Conditioning.Output(),
             ],
         )
 
@@ -99,7 +99,7 @@ class StableCascade_StageB_Conditioning_V3(io.ComfyNodeV3):
         c = []
         for t in conditioning:
             d = t[1].copy()
-            d['stable_cascade_prior'] = stage_c['samples']
+            d["stable_cascade_prior"] = stage_c["samples"]
             n = [t[0], d]
             c.append(n)
         return io.NodeOutput(c)
@@ -128,7 +128,7 @@ class StableCascade_SuperResolutionControlnet_V3(io.ComfyNodeV3):
         width = image.shape[-2]
         height = image.shape[-3]
         batch_size = image.shape[0]
-        controlnet_input = vae.encode(image[:,:,:,:3]).movedim(1, -1)
+        controlnet_input = vae.encode(image[:, :, :, :3]).movedim(1, -1)
 
         c_latent = torch.zeros([batch_size, 16, height // 16, width // 16])
         b_latent = torch.zeros([batch_size, 4, height // 2, width // 2])

comfy_extras/v3/nodes_webcam.py

@@ -1,14 +1,13 @@
 import hashlib
-import torch
 
 import numpy as np
+import torch
 from PIL import Image, ImageOps, ImageSequence
 
-from comfy_api.v3 import io
-import nodes
 import folder_paths
 import node_helpers
-
+import nodes
+from comfy_api.v3 import io
 
 MAX_RESOLUTION = nodes.MAX_RESOLUTION
 
@@ -51,12 +50,12 @@ class WebcamCapture_V3(io.ComfyNodeV3):
         output_masks = []
         w, h = None, None
 
-        excluded_formats = ['MPO']
+        excluded_formats = ["MPO"]
 
         for i in ImageSequence.Iterator(img):
             i = node_helpers.pillow(ImageOps.exif_transpose, i)
 
-            if i.mode == 'I':
+            if i.mode == "I":
                 i = i.point(lambda i: i * (1 / 255))
             image = i.convert("RGB")
 
@@ -69,12 +68,12 @@ class WebcamCapture_V3(io.ComfyNodeV3):
 
             image = np.array(image).astype(np.float32) / 255.0
             image = torch.from_numpy(image)[None,]
-            if 'A' in i.getbands():
+            if "A" in i.getbands():
-                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
-            elif i.mode == 'P' and 'transparency' in i.info:
+            elif i.mode == "P" and "transparency" in i.info:
-                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = np.array(i.convert("RGBA").getchannel("A")).astype(np.float32) / 255.0
-                mask = 1. - torch.from_numpy(mask)
+                mask = 1.0 - torch.from_numpy(mask)
             else:
                 mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
             output_images.append(image)
@@ -93,7 +92,7 @@ class WebcamCapture_V3(io.ComfyNodeV3):
     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:
+        with open(image_path, "rb") as f:
             m.update(f.read())
         return m.digest().hex()
 

nodes.py

@@ -2299,9 +2299,11 @@ def init_builtin_extra_nodes():
         "nodes_tcfg.py",
         "nodes_v3_test.py",
         "nodes_v1_test.py",
+        "v3/nodes_audio.py",
         "v3/nodes_controlnet.py",
         "v3/nodes_images.py",
         "v3/nodes_mask.py",
+        "v3/nodes_primitive.py",
         "v3/nodes_webcam.py",
         "v3/nodes_stable_cascade.py",
     ]

pyproject.toml

@@ -12,6 +12,8 @@ documentation = "https://docs.comfy.org/"
 
 [tool.ruff]
 lint.select = [
+  "E",    # pycodestyle errors
+  "I",    # isort
   "N805", # invalid-first-argument-name-for-method
   "S307", # suspicious-eval-usage
   "S102", # exec
@@ -22,3 +24,8 @@ lint.select = [
   "F",
 ]
 exclude = ["*.ipynb"]
+line-length = 120
+lint.pycodestyle.ignore-overlong-task-comments = true
+
+[tool.ruff.lint.per-file-ignores]
+"!comfy_extras/v3/*" = ["E", "I"]  # enable these rules only for V3 nodes