Merge 51119d3283056817b6260107f535ae356df2ee62 into fd271dedfde6e192a1f1a025521070876e89e04a

* feat(api-nodes): add support for seedance-1-0-pro-fast model

* feat(api-nodes): add support for seedream-4.5 model

comfy/lora.py

@@ -320,6 +320,7 @@ def model_lora_keys_unet(model, key_map={}):
                 to = diffusers_keys[k]
                 key_lora = k[:-len(".weight")]
                 key_map["diffusion_model.{}".format(key_lora)] = to
+                key_map["transformer.{}".format(key_lora)] = to
                 key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = to
 
     if isinstance(model, comfy.model_base.Kandinsky5):

comfy_api/latest/__init__.py

@@ -5,9 +5,9 @@ from typing import Type, TYPE_CHECKING
 from comfy_api.internal import ComfyAPIBase
 from comfy_api.internal.singleton import ProxiedSingleton
 from comfy_api.internal.async_to_sync import create_sync_class
-from comfy_api.latest._input import ImageInput, AudioInput, MaskInput, LatentInput, VideoInput
-from comfy_api.latest._input_impl import VideoFromFile, VideoFromComponents
-from comfy_api.latest._util import VideoCodec, VideoContainer, VideoComponents, MESH, VOXEL
+from ._input import ImageInput, AudioInput, MaskInput, LatentInput, VideoInput
+from ._input_impl import VideoFromFile, VideoFromComponents
+from ._util import VideoCodec, VideoContainer, VideoComponents, MESH, VOXEL
 from . import _io_public as io
 from . import _ui_public as ui
 # from comfy_api.latest._resources import _RESOURCES as resources  #noqa: F401
@@ -80,7 +80,7 @@ class ComfyExtension(ABC):
     async def on_load(self) -> None:
         """
         Called when an extension is loaded.
-        This should be used to initialize any global resources neeeded by the extension.
+        This should be used to initialize any global resources needed by the extension.
         """
 
     @abstractmethod

comfy_api/latest/_input/video_types.py

@@ -4,7 +4,7 @@ from fractions import Fraction
 from typing import Optional, Union, IO
 import io
 import av
-from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
+from .._util import VideoContainer, VideoCodec, VideoComponents
 
 class VideoInput(ABC):
     """

comfy_api/latest/_input_impl/video_types.py

@@ -3,14 +3,14 @@ from av.container import InputContainer
 from av.subtitles.stream import SubtitleStream
 from fractions import Fraction
 from typing import Optional
-from comfy_api.latest._input import AudioInput, VideoInput
+from .._input import AudioInput, VideoInput
 import av
 import io
 import json
 import numpy as np
 import math
 import torch
-from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents
+from .._util import VideoContainer, VideoCodec, VideoComponents
 
 
 def container_to_output_format(container_format: str | None) -> str | None:

comfy_api/latest/_io.py

@@ -26,7 +26,7 @@ if TYPE_CHECKING:
     from comfy_api.input import VideoInput
 from comfy_api.internal import (_ComfyNodeInternal, _NodeOutputInternal, classproperty, copy_class, first_real_override, is_class,
     prune_dict, shallow_clone_class)
-from comfy_api.latest._resources import Resources, ResourcesLocal
+from ._resources import Resources, ResourcesLocal
 from comfy_execution.graph_utils import ExecutionBlocker
 from ._util import MESH, VOXEL
 

comfy_api/latest/_ui.py

@@ -22,7 +22,7 @@ import folder_paths
 
 # used for image preview
 from comfy.cli_args import args
-from comfy_api.latest._io import ComfyNode, FolderType, Image, _UIOutput
+from ._io import ComfyNode, FolderType, Image, _UIOutput
 
 
 class SavedResult(dict):

comfy_api/latest/_util/video_types.py

@@ -3,7 +3,7 @@ from dataclasses import dataclass
 from enum import Enum
 from fractions import Fraction
 from typing import Optional
-from comfy_api.latest._input import ImageInput, AudioInput
+from .._input import ImageInput, AudioInput
 
 class VideoCodec(str, Enum):
     AUTO = "auto"

comfy_api_nodes/apis/bytedance_api.py

@@ -0,0 +1,144 @@
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+
+class Text2ImageTaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    prompt: str = Field(...)
+    response_format: str | None = Field("url")
+    size: str | None = Field(None)
+    seed: int | None = Field(0, ge=0, le=2147483647)
+    guidance_scale: float | None = Field(..., ge=1.0, le=10.0)
+    watermark: bool | None = Field(True)
+
+
+class Image2ImageTaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    prompt: str = Field(...)
+    response_format: str | None = Field("url")
+    image: str = Field(..., description="Base64 encoded string or image URL")
+    size: str | None = Field("adaptive")
+    seed: int | None = Field(..., ge=0, le=2147483647)
+    guidance_scale: float | None = Field(..., ge=1.0, le=10.0)
+    watermark: bool | None = Field(True)
+
+
+class Seedream4Options(BaseModel):
+    max_images: int = Field(15)
+
+
+class Seedream4TaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    prompt: str = Field(...)
+    response_format: str = Field("url")
+    image: list[str] | None = Field(None, description="Image URLs")
+    size: str = Field(...)
+    seed: int = Field(..., ge=0, le=2147483647)
+    sequential_image_generation: str = Field("disabled")
+    sequential_image_generation_options: Seedream4Options = Field(Seedream4Options(max_images=15))
+    watermark: bool = Field(True)
+
+
+class ImageTaskCreationResponse(BaseModel):
+    model: str = Field(...)
+    created: int = Field(..., description="Unix timestamp (in seconds) indicating time when the request was created.")
+    data: list = Field([], description="Contains information about the generated image(s).")
+    error: dict = Field({}, description="Contains `code` and `message` fields in case of error.")
+
+
+class TaskTextContent(BaseModel):
+    type: str = Field("text")
+    text: str = Field(...)
+
+
+class TaskImageContentUrl(BaseModel):
+    url: str = Field(...)
+
+
+class TaskImageContent(BaseModel):
+    type: str = Field("image_url")
+    image_url: TaskImageContentUrl = Field(...)
+    role: Literal["first_frame", "last_frame", "reference_image"] | None = Field(None)
+
+
+class Text2VideoTaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    content: list[TaskTextContent] = Field(..., min_length=1)
+
+
+class Image2VideoTaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    content: list[TaskTextContent | TaskImageContent] = Field(..., min_length=2)
+
+
+class TaskCreationResponse(BaseModel):
+    id: str = Field(...)
+
+
+class TaskStatusError(BaseModel):
+    code: str = Field(...)
+    message: str = Field(...)
+
+
+class TaskStatusResult(BaseModel):
+    video_url: str = Field(...)
+
+
+class TaskStatusResponse(BaseModel):
+    id: str = Field(...)
+    model: str = Field(...)
+    status: Literal["queued", "running", "cancelled", "succeeded", "failed"] = Field(...)
+    error: TaskStatusError | None = Field(None)
+    content: TaskStatusResult | None = Field(None)
+
+
+RECOMMENDED_PRESETS = [
+    ("1024x1024 (1:1)", 1024, 1024),
+    ("864x1152 (3:4)", 864, 1152),
+    ("1152x864 (4:3)", 1152, 864),
+    ("1280x720 (16:9)", 1280, 720),
+    ("720x1280 (9:16)", 720, 1280),
+    ("832x1248 (2:3)", 832, 1248),
+    ("1248x832 (3:2)", 1248, 832),
+    ("1512x648 (21:9)", 1512, 648),
+    ("2048x2048 (1:1)", 2048, 2048),
+    ("Custom", None, None),
+]
+
+RECOMMENDED_PRESETS_SEEDREAM_4 = [
+    ("2048x2048 (1:1)", 2048, 2048),
+    ("2304x1728 (4:3)", 2304, 1728),
+    ("1728x2304 (3:4)", 1728, 2304),
+    ("2560x1440 (16:9)", 2560, 1440),
+    ("1440x2560 (9:16)", 1440, 2560),
+    ("2496x1664 (3:2)", 2496, 1664),
+    ("1664x2496 (2:3)", 1664, 2496),
+    ("3024x1296 (21:9)", 3024, 1296),
+    ("4096x4096 (1:1)", 4096, 4096),
+    ("Custom", None, None),
+]
+
+# The time in this dictionary are given for 10 seconds duration.
+VIDEO_TASKS_EXECUTION_TIME = {
+    "seedance-1-0-lite-t2v-250428": {
+        "480p": 40,
+        "720p": 60,
+        "1080p": 90,
+    },
+    "seedance-1-0-lite-i2v-250428": {
+        "480p": 40,
+        "720p": 60,
+        "1080p": 90,
+    },
+    "seedance-1-0-pro-250528": {
+        "480p": 70,
+        "720p": 85,
+        "1080p": 115,
+    },
+    "seedance-1-0-pro-fast-251015": {
+        "480p": 50,
+        "720p": 65,
+        "1080p": 100,
+    },
+}

comfy_api_nodes/apis/gemini_api.py

@@ -84,15 +84,7 @@ class GeminiSystemInstructionContent(BaseModel):
         description="A list of ordered parts that make up a single message. "
         "Different parts may have different IANA MIME types.",
     )
-    role: GeminiRole = Field(
-        ...,
-        description="The identity of the entity that creates the message. "
-        "The following values are supported: "
-        "user: This indicates that the message is sent by a real person, typically a user-generated message. "
-        "model: This indicates that the message is generated by the model. "
-        "The model value is used to insert messages from model into the conversation during multi-turn conversations. "
-        "For non-multi-turn conversations, this field can be left blank or unset.",
-    )
+    role: GeminiRole | None = Field(..., description="The role field of systemInstruction may be ignored.")
 
 
 class GeminiFunctionDeclaration(BaseModel):

comfy_api_nodes/apis/veo_api.py

@@ -85,7 +85,7 @@ class Response1(BaseModel):
     raiMediaFilteredReasons: Optional[list[str]] = Field(
         None, description='Reasons why media was filtered by responsible AI policies'
     )
-    videos: Optional[list[Video]] = None
+    videos: Optional[list[Video]] = Field(None)
 
 
 class VeoGenVidPollResponse(BaseModel):

comfy_api_nodes/nodes_bytedance.py

@@ -1,13 +1,27 @@
 import logging
 import math
-from enum import Enum
-from typing import Literal, Optional, Union
 
 import torch
-from pydantic import BaseModel, Field
 from typing_extensions import override
 
-from comfy_api.latest import IO, ComfyExtension
+from comfy_api.latest import IO, ComfyExtension, Input
+from comfy_api_nodes.apis.bytedance_api import (
+    RECOMMENDED_PRESETS,
+    RECOMMENDED_PRESETS_SEEDREAM_4,
+    VIDEO_TASKS_EXECUTION_TIME,
+    Image2ImageTaskCreationRequest,
+    Image2VideoTaskCreationRequest,
+    ImageTaskCreationResponse,
+    Seedream4Options,
+    Seedream4TaskCreationRequest,
+    TaskCreationResponse,
+    TaskImageContent,
+    TaskImageContentUrl,
+    TaskStatusResponse,
+    TaskTextContent,
+    Text2ImageTaskCreationRequest,
+    Text2VideoTaskCreationRequest,
+)
 from comfy_api_nodes.util import (
     ApiEndpoint,
     download_url_to_image_tensor,
@@ -29,162 +43,6 @@ BYTEPLUS_TASK_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks"
 BYTEPLUS_TASK_STATUS_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks"  # + /{task_id}
 
 
-class Text2ImageModelName(str, Enum):
-    seedream_3 = "seedream-3-0-t2i-250415"
-
-
-class Image2ImageModelName(str, Enum):
-    seededit_3 = "seededit-3-0-i2i-250628"
-
-
-class Text2VideoModelName(str, Enum):
-    seedance_1_pro = "seedance-1-0-pro-250528"
-    seedance_1_lite = "seedance-1-0-lite-t2v-250428"
-
-
-class Image2VideoModelName(str, Enum):
-    """note(August 31): Pro model only supports FirstFrame: https://docs.byteplus.com/en/docs/ModelArk/1520757"""
-
-    seedance_1_pro = "seedance-1-0-pro-250528"
-    seedance_1_lite = "seedance-1-0-lite-i2v-250428"
-
-
-class Text2ImageTaskCreationRequest(BaseModel):
-    model: Text2ImageModelName = Text2ImageModelName.seedream_3
-    prompt: str = Field(...)
-    response_format: Optional[str] = Field("url")
-    size: Optional[str] = Field(None)
-    seed: Optional[int] = Field(0, ge=0, le=2147483647)
-    guidance_scale: Optional[float] = Field(..., ge=1.0, le=10.0)
-    watermark: Optional[bool] = Field(True)
-
-
-class Image2ImageTaskCreationRequest(BaseModel):
-    model: Image2ImageModelName = Image2ImageModelName.seededit_3
-    prompt: str = Field(...)
-    response_format: Optional[str] = Field("url")
-    image: str = Field(..., description="Base64 encoded string or image URL")
-    size: Optional[str] = Field("adaptive")
-    seed: Optional[int] = Field(..., ge=0, le=2147483647)
-    guidance_scale: Optional[float] = Field(..., ge=1.0, le=10.0)
-    watermark: Optional[bool] = Field(True)
-
-
-class Seedream4Options(BaseModel):
-    max_images: int = Field(15)
-
-
-class Seedream4TaskCreationRequest(BaseModel):
-    model: str = Field("seedream-4-0-250828")
-    prompt: str = Field(...)
-    response_format: str = Field("url")
-    image: Optional[list[str]] = Field(None, description="Image URLs")
-    size: str = Field(...)
-    seed: int = Field(..., ge=0, le=2147483647)
-    sequential_image_generation: str = Field("disabled")
-    sequential_image_generation_options: Seedream4Options = Field(Seedream4Options(max_images=15))
-    watermark: bool = Field(True)
-
-
-class ImageTaskCreationResponse(BaseModel):
-    model: str = Field(...)
-    created: int = Field(..., description="Unix timestamp (in seconds) indicating time when the request was created.")
-    data: list = Field([], description="Contains information about the generated image(s).")
-    error: dict = Field({}, description="Contains `code` and `message` fields in case of error.")
-
-
-class TaskTextContent(BaseModel):
-    type: str = Field("text")
-    text: str = Field(...)
-
-
-class TaskImageContentUrl(BaseModel):
-    url: str = Field(...)
-
-
-class TaskImageContent(BaseModel):
-    type: str = Field("image_url")
-    image_url: TaskImageContentUrl = Field(...)
-    role: Optional[Literal["first_frame", "last_frame", "reference_image"]] = Field(None)
-
-
-class Text2VideoTaskCreationRequest(BaseModel):
-    model: Text2VideoModelName = Text2VideoModelName.seedance_1_pro
-    content: list[TaskTextContent] = Field(..., min_length=1)
-
-
-class Image2VideoTaskCreationRequest(BaseModel):
-    model: Image2VideoModelName = Image2VideoModelName.seedance_1_pro
-    content: list[Union[TaskTextContent, TaskImageContent]] = Field(..., min_length=2)
-
-
-class TaskCreationResponse(BaseModel):
-    id: str = Field(...)
-
-
-class TaskStatusError(BaseModel):
-    code: str = Field(...)
-    message: str = Field(...)
-
-
-class TaskStatusResult(BaseModel):
-    video_url: str = Field(...)
-
-
-class TaskStatusResponse(BaseModel):
-    id: str = Field(...)
-    model: str = Field(...)
-    status: Literal["queued", "running", "cancelled", "succeeded", "failed"] = Field(...)
-    error: Optional[TaskStatusError] = Field(None)
-    content: Optional[TaskStatusResult] = Field(None)
-
-
-RECOMMENDED_PRESETS = [
-    ("1024x1024 (1:1)", 1024, 1024),
-    ("864x1152 (3:4)", 864, 1152),
-    ("1152x864 (4:3)", 1152, 864),
-    ("1280x720 (16:9)", 1280, 720),
-    ("720x1280 (9:16)", 720, 1280),
-    ("832x1248 (2:3)", 832, 1248),
-    ("1248x832 (3:2)", 1248, 832),
-    ("1512x648 (21:9)", 1512, 648),
-    ("2048x2048 (1:1)", 2048, 2048),
-    ("Custom", None, None),
-]
-
-RECOMMENDED_PRESETS_SEEDREAM_4 = [
-    ("2048x2048 (1:1)", 2048, 2048),
-    ("2304x1728 (4:3)", 2304, 1728),
-    ("1728x2304 (3:4)", 1728, 2304),
-    ("2560x1440 (16:9)", 2560, 1440),
-    ("1440x2560 (9:16)", 1440, 2560),
-    ("2496x1664 (3:2)", 2496, 1664),
-    ("1664x2496 (2:3)", 1664, 2496),
-    ("3024x1296 (21:9)", 3024, 1296),
-    ("4096x4096 (1:1)", 4096, 4096),
-    ("Custom", None, None),
-]
-
-# The time in this dictionary are given for 10 seconds duration.
-VIDEO_TASKS_EXECUTION_TIME = {
-    "seedance-1-0-lite-t2v-250428": {
-        "480p": 40,
-        "720p": 60,
-        "1080p": 90,
-    },
-    "seedance-1-0-lite-i2v-250428": {
-        "480p": 40,
-        "720p": 60,
-        "1080p": 90,
-    },
-    "seedance-1-0-pro-250528": {
-        "480p": 70,
-        "720p": 85,
-        "1080p": 115,
-    },
-}
-
-
 def get_image_url_from_response(response: ImageTaskCreationResponse) -> str:
     if response.error:
         error_msg = f"ByteDance request failed. Code: {response.error['code']}, message: {response.error['message']}"
@@ -194,13 +52,6 @@ def get_image_url_from_response(response: ImageTaskCreationResponse) -> str:
     return response.data[0]["url"]
 
 
-def get_video_url_from_task_status(response: TaskStatusResponse) -> Union[str, None]:
-    """Returns the video URL from the task status response if it exists."""
-    if hasattr(response, "content") and response.content:
-        return response.content.video_url
-    return None
-
-
 class ByteDanceImageNode(IO.ComfyNode):
 
     @classmethod
@@ -211,12 +62,7 @@ class ByteDanceImageNode(IO.ComfyNode):
             category="api node/image/ByteDance",
             description="Generate images using ByteDance models via api based on prompt",
             inputs=[
-                IO.Combo.Input(
-                    "model",
-                    options=Text2ImageModelName,
-                    default=Text2ImageModelName.seedream_3,
-                    tooltip="Model name",
-                ),
+                IO.Combo.Input("model", options=["seedream-3-0-t2i-250415"]),
                 IO.String.Input(
                     "prompt",
                     multiline=True,
@@ -335,12 +181,7 @@ class ByteDanceImageEditNode(IO.ComfyNode):
             category="api node/image/ByteDance",
             description="Edit images using ByteDance models via api based on prompt",
             inputs=[
-                IO.Combo.Input(
-                    "model",
-                    options=Image2ImageModelName,
-                    default=Image2ImageModelName.seededit_3,
-                    tooltip="Model name",
-                ),
+                IO.Combo.Input("model", options=["seededit-3-0-i2i-250628"]),
                 IO.Image.Input(
                     "image",
                     tooltip="The base image to edit",
@@ -394,7 +235,7 @@ class ByteDanceImageEditNode(IO.ComfyNode):
     async def execute(
         cls,
         model: str,
-        image: torch.Tensor,
+        image: Input.Image,
         prompt: str,
         seed: int,
         guidance_scale: float,
@@ -434,7 +275,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=["seedream-4-0-250828"],
+                    options=["seedream-4-5-251128", "seedream-4-0-250828"],
                     tooltip="Model name",
                 ),
                 IO.String.Input(
@@ -459,7 +300,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
                     default=2048,
                     min=1024,
                     max=4096,
-                    step=64,
+                    step=8,
                     tooltip="Custom width for image. Value is working only if `size_preset` is set to `Custom`",
                     optional=True,
                 ),
@@ -468,7 +309,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
                     default=2048,
                     min=1024,
                     max=4096,
-                    step=64,
+                    step=8,
                     tooltip="Custom height for image. Value is working only if `size_preset` is set to `Custom`",
                     optional=True,
                 ),
@@ -532,7 +373,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
         cls,
         model: str,
         prompt: str,
-        image: torch.Tensor = None,
+        image: Input.Image | None = None,
         size_preset: str = RECOMMENDED_PRESETS_SEEDREAM_4[0][0],
         width: int = 2048,
         height: int = 2048,
@@ -555,6 +396,18 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
                 raise ValueError(
                     f"Custom size out of range: {w}x{h}. " "Both width and height must be between 1024 and 4096 pixels."
                 )
+        out_num_pixels = w * h
+        mp_provided = out_num_pixels / 1_000_000.0
+        if "seedream-4-5" in model and out_num_pixels < 3686400:
+            raise ValueError(
+                f"Minimum image resolution that Seedream 4.5 can generate is 3.68MP, "
+                f"but {mp_provided:.2f}MP provided."
+            )
+        if "seedream-4-0" in model and out_num_pixels < 921600:
+            raise ValueError(
+                f"Minimum image resolution that the selected model can generate is 0.92MP, "
+                f"but {mp_provided:.2f}MP provided."
+            )
         n_input_images = get_number_of_images(image) if image is not None else 0
         if n_input_images > 10:
             raise ValueError(f"Maximum of 10 reference images are supported, but {n_input_images} received.")
@@ -607,9 +460,8 @@ class ByteDanceTextToVideoNode(IO.ComfyNode):
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=Text2VideoModelName,
-                    default=Text2VideoModelName.seedance_1_pro,
-                    tooltip="Model name",
+                    options=["seedance-1-0-pro-250528", "seedance-1-0-lite-t2v-250428", "seedance-1-0-pro-fast-251015"],
+                    default="seedance-1-0-pro-fast-251015",
                 ),
                 IO.String.Input(
                     "prompt",
@@ -714,9 +566,8 @@ class ByteDanceImageToVideoNode(IO.ComfyNode):
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=Image2VideoModelName,
-                    default=Image2VideoModelName.seedance_1_pro,
-                    tooltip="Model name",
+                    options=["seedance-1-0-pro-250528", "seedance-1-0-lite-t2v-250428", "seedance-1-0-pro-fast-251015"],
+                    default="seedance-1-0-pro-fast-251015",
                 ),
                 IO.String.Input(
                     "prompt",
@@ -787,7 +638,7 @@ class ByteDanceImageToVideoNode(IO.ComfyNode):
         cls,
         model: str,
         prompt: str,
-        image: torch.Tensor,
+        image: Input.Image,
         resolution: str,
         aspect_ratio: str,
         duration: int,
@@ -833,9 +684,8 @@ class ByteDanceFirstLastFrameNode(IO.ComfyNode):
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=[model.value for model in Image2VideoModelName],
-                    default=Image2VideoModelName.seedance_1_lite.value,
-                    tooltip="Model name",
+                    options=["seedance-1-0-pro-250528", "seedance-1-0-lite-i2v-250428"],
+                    default="seedance-1-0-lite-i2v-250428",
                 ),
                 IO.String.Input(
                     "prompt",
@@ -910,8 +760,8 @@ class ByteDanceFirstLastFrameNode(IO.ComfyNode):
         cls,
         model: str,
         prompt: str,
-        first_frame: torch.Tensor,
-        last_frame: torch.Tensor,
+        first_frame: Input.Image,
+        last_frame: Input.Image,
         resolution: str,
         aspect_ratio: str,
         duration: int,
@@ -968,9 +818,8 @@ class ByteDanceImageReferenceNode(IO.ComfyNode):
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=[Image2VideoModelName.seedance_1_lite.value],
-                    default=Image2VideoModelName.seedance_1_lite.value,
-                    tooltip="Model name",
+                    options=["seedance-1-0-pro-250528", "seedance-1-0-lite-i2v-250428"],
+                    default="seedance-1-0-lite-i2v-250428",
                 ),
                 IO.String.Input(
                     "prompt",
@@ -1034,7 +883,7 @@ class ByteDanceImageReferenceNode(IO.ComfyNode):
         cls,
         model: str,
         prompt: str,
-        images: torch.Tensor,
+        images: Input.Image,
         resolution: str,
         aspect_ratio: str,
         duration: int,
@@ -1069,8 +918,8 @@ class ByteDanceImageReferenceNode(IO.ComfyNode):
 
 async def process_video_task(
     cls: type[IO.ComfyNode],
-    payload: Union[Text2VideoTaskCreationRequest, Image2VideoTaskCreationRequest],
-    estimated_duration: Optional[int],
+    payload: Text2VideoTaskCreationRequest | Image2VideoTaskCreationRequest,
+    estimated_duration: int | None,
 ) -> IO.NodeOutput:
     initial_response = await sync_op(
         cls,
@@ -1085,7 +934,7 @@ async def process_video_task(
         estimated_duration=estimated_duration,
         response_model=TaskStatusResponse,
     )
-    return IO.NodeOutput(await download_url_to_video_output(get_video_url_from_task_status(response)))
+    return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
 
 
 def raise_if_text_params(prompt: str, text_params: list[str]) -> None:

comfy_api_nodes/nodes_gemini.py

@@ -13,8 +13,7 @@ import torch
 from typing_extensions import override
 
 import folder_paths
-from comfy_api.latest import IO, ComfyExtension, Input
-from comfy_api.util import VideoCodec, VideoContainer
+from comfy_api.latest import IO, ComfyExtension, Input, Types
 from comfy_api_nodes.apis.gemini_api import (
     GeminiContent,
     GeminiFileData,
@@ -27,6 +26,8 @@ from comfy_api_nodes.apis.gemini_api import (
     GeminiMimeType,
     GeminiPart,
     GeminiRole,
+    GeminiSystemInstructionContent,
+    GeminiTextPart,
     Modality,
 )
 from comfy_api_nodes.util import (
@@ -43,6 +44,14 @@ from comfy_api_nodes.util import (
 
 GEMINI_BASE_ENDPOINT = "/proxy/vertexai/gemini"
 GEMINI_MAX_INPUT_FILE_SIZE = 20 * 1024 * 1024  # 20 MB
+GEMINI_IMAGE_SYS_PROMPT = (
+    "You are an expert image-generation engine. You must ALWAYS produce an image.\n"
+    "Interpret all user input—regardless of "
+    "format, intent, or abstraction—as literal visual directives for image composition.\n"
+    "If a prompt is conversational or lacks specific visual details, "
+    "you must creatively invent a concrete visual scenario that depicts the concept.\n"
+    "Prioritize generating the visual representation above any text, formatting, or conversational requests."
+)
 
 
 class GeminiModel(str, Enum):
@@ -68,7 +77,7 @@ class GeminiImageModel(str, Enum):
 
 async def create_image_parts(
     cls: type[IO.ComfyNode],
-    images: torch.Tensor,
+    images: Input.Image,
     image_limit: int = 0,
 ) -> list[GeminiPart]:
     image_parts: list[GeminiPart] = []
@@ -154,8 +163,8 @@ def get_text_from_response(response: GeminiGenerateContentResponse) -> str:
     return "\n".join([part.text for part in parts])
 
 
-def get_image_from_response(response: GeminiGenerateContentResponse) -> torch.Tensor:
-    image_tensors: list[torch.Tensor] = []
+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)
@@ -277,6 +286,13 @@ class GeminiNode(IO.ComfyNode):
                     tooltip="Optional file(s) to use as context for the model. "
                     "Accepts inputs from the Gemini Generate Content Input Files node.",
                 ),
+                IO.String.Input(
+                    "system_prompt",
+                    multiline=True,
+                    default="",
+                    optional=True,
+                    tooltip="Foundational instructions that dictate an AI's behavior.",
+                ),
             ],
             outputs=[
                 IO.String.Output(),
@@ -293,7 +309,9 @@ class GeminiNode(IO.ComfyNode):
     def create_video_parts(cls, video_input: Input.Video) -> list[GeminiPart]:
         """Convert video input to Gemini API compatible parts."""
 
-        base_64_string = video_to_base64_string(video_input, container_format=VideoContainer.MP4, codec=VideoCodec.H264)
+        base_64_string = video_to_base64_string(
+            video_input, container_format=Types.VideoContainer.MP4, codec=Types.VideoCodec.H264
+        )
         return [
             GeminiPart(
                 inlineData=GeminiInlineData(
@@ -343,10 +361,11 @@ class GeminiNode(IO.ComfyNode):
         prompt: str,
         model: str,
         seed: int,
-        images: torch.Tensor | None = None,
+        images: Input.Image | None = None,
         audio: Input.Audio | None = None,
         video: Input.Video | None = None,
         files: list[GeminiPart] | None = None,
+        system_prompt: str = "",
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=False)
 
@@ -363,7 +382,10 @@ class GeminiNode(IO.ComfyNode):
         if files is not None:
             parts.extend(files)
 
-        # Create response
+        gemini_system_prompt = None
+        if system_prompt:
+            gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)
+
         response = await sync_op(
             cls,
             endpoint=ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model}", method="POST"),
@@ -373,7 +395,8 @@ class GeminiNode(IO.ComfyNode):
                         role=GeminiRole.user,
                         parts=parts,
                     )
-                ]
+                ],
+                systemInstruction=gemini_system_prompt,
             ),
             response_model=GeminiGenerateContentResponse,
             price_extractor=calculate_tokens_price,
@@ -523,6 +546,13 @@ class GeminiImage(IO.ComfyNode):
                     "'IMAGE+TEXT' to return both the generated image and a text response.",
                     optional=True,
                 ),
+                IO.String.Input(
+                    "system_prompt",
+                    multiline=True,
+                    default=GEMINI_IMAGE_SYS_PROMPT,
+                    optional=True,
+                    tooltip="Foundational instructions that dictate an AI's behavior.",
+                ),
             ],
             outputs=[
                 IO.Image.Output(),
@@ -542,10 +572,11 @@ class GeminiImage(IO.ComfyNode):
         prompt: str,
         model: str,
         seed: int,
-        images: torch.Tensor | None = None,
+        images: Input.Image | None = None,
         files: list[GeminiPart] | None = None,
         aspect_ratio: str = "auto",
         response_modalities: str = "IMAGE+TEXT",
+        system_prompt: str = "",
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=True, min_length=1)
         parts: list[GeminiPart] = [GeminiPart(text=prompt)]
@@ -559,6 +590,10 @@ class GeminiImage(IO.ComfyNode):
         if files is not None:
             parts.extend(files)
 
+        gemini_system_prompt = None
+        if system_prompt:
+            gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)
+
         response = await sync_op(
             cls,
             endpoint=ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model}", method="POST"),
@@ -570,6 +605,7 @@ class GeminiImage(IO.ComfyNode):
                     responseModalities=(["IMAGE"] if response_modalities == "IMAGE" else ["TEXT", "IMAGE"]),
                     imageConfig=None if aspect_ratio == "auto" else image_config,
                 ),
+                systemInstruction=gemini_system_prompt,
             ),
             response_model=GeminiGenerateContentResponse,
             price_extractor=calculate_tokens_price,
@@ -640,6 +676,13 @@ class GeminiImage2(IO.ComfyNode):
                     tooltip="Optional file(s) to use as context for the model. "
                     "Accepts inputs from the Gemini Generate Content Input Files node.",
                 ),
+                IO.String.Input(
+                    "system_prompt",
+                    multiline=True,
+                    default=GEMINI_IMAGE_SYS_PROMPT,
+                    optional=True,
+                    tooltip="Foundational instructions that dictate an AI's behavior.",
+                ),
             ],
             outputs=[
                 IO.Image.Output(),
@@ -662,8 +705,9 @@ class GeminiImage2(IO.ComfyNode):
         aspect_ratio: str,
         resolution: str,
         response_modalities: str,
-        images: torch.Tensor | None = None,
+        images: Input.Image | None = None,
         files: list[GeminiPart] | None = None,
+        system_prompt: str = "",
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=True, min_length=1)
 
@@ -679,6 +723,10 @@ class GeminiImage2(IO.ComfyNode):
         if aspect_ratio != "auto":
             image_config.aspectRatio = aspect_ratio
 
+        gemini_system_prompt = None
+        if system_prompt:
+            gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)
+
         response = await sync_op(
             cls,
             ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model}", method="POST"),
@@ -690,6 +738,7 @@ class GeminiImage2(IO.ComfyNode):
                     responseModalities=(["IMAGE"] if response_modalities == "IMAGE" else ["TEXT", "IMAGE"]),
                     imageConfig=image_config,
                 ),
+                systemInstruction=gemini_system_prompt,
             ),
             response_model=GeminiGenerateContentResponse,
             price_extractor=calculate_tokens_price,

comfy_api_nodes/nodes_ltxv.py

@@ -1,12 +1,9 @@
 from io import BytesIO
-from typing import Optional
 
-import torch
 from pydantic import BaseModel, Field
 from typing_extensions import override
 
-from comfy_api.input_impl import VideoFromFile
-from comfy_api.latest import IO, ComfyExtension
+from comfy_api.latest import IO, ComfyExtension, Input, InputImpl
 from comfy_api_nodes.util import (
     ApiEndpoint,
     get_number_of_images,
@@ -26,9 +23,9 @@ class ExecuteTaskRequest(BaseModel):
     model: str = Field(...)
     duration: int = Field(...)
     resolution: str = Field(...)
-    fps: Optional[int] = Field(25)
-    generate_audio: Optional[bool] = Field(True)
-    image_uri: Optional[str] = Field(None)
+    fps: int | None = Field(25)
+    generate_audio: bool | None = Field(True)
+    image_uri: str | None = Field(None)
 
 
 class TextToVideoNode(IO.ComfyNode):
@@ -103,7 +100,7 @@ class TextToVideoNode(IO.ComfyNode):
             as_binary=True,
             max_retries=1,
         )
-        return IO.NodeOutput(VideoFromFile(BytesIO(response)))
+        return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(response)))
 
 
 class ImageToVideoNode(IO.ComfyNode):
@@ -153,7 +150,7 @@ class ImageToVideoNode(IO.ComfyNode):
     @classmethod
     async def execute(
         cls,
-        image: torch.Tensor,
+        image: Input.Image,
         model: str,
         prompt: str,
         duration: int,
@@ -183,7 +180,7 @@ class ImageToVideoNode(IO.ComfyNode):
             as_binary=True,
             max_retries=1,
         )
-        return IO.NodeOutput(VideoFromFile(BytesIO(response)))
+        return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(response)))
 
 
 class LtxvApiExtension(ComfyExtension):

comfy_api_nodes/nodes_moonvalley.py

@@ -1,11 +1,8 @@
 import logging
-from typing import Optional
 
-import torch
 from typing_extensions import override
 
-from comfy_api.input import VideoInput
-from comfy_api.latest import IO, ComfyExtension
+from comfy_api.latest import IO, ComfyExtension, Input
 from comfy_api_nodes.apis import (
     MoonvalleyPromptResponse,
     MoonvalleyTextToVideoInferenceParams,
@@ -61,7 +58,7 @@ def validate_task_creation_response(response) -> None:
         raise RuntimeError(error_msg)
 
 
-def validate_video_to_video_input(video: VideoInput) -> VideoInput:
+def validate_video_to_video_input(video: Input.Video) -> Input.Video:
     """
     Validates and processes video input for Moonvalley Video-to-Video generation.
 
@@ -82,7 +79,7 @@ def validate_video_to_video_input(video: VideoInput) -> VideoInput:
     return _validate_and_trim_duration(video)
 
 
-def _get_video_dimensions(video: VideoInput) -> tuple[int, int]:
+def _get_video_dimensions(video: Input.Video) -> tuple[int, int]:
     """Extracts video dimensions with error handling."""
     try:
         return video.get_dimensions()
@@ -106,7 +103,7 @@ def _validate_video_dimensions(width: int, height: int) -> None:
         raise ValueError(f"Resolution {width}x{height} not supported. Supported: {supported_list}")
 
 
-def _validate_and_trim_duration(video: VideoInput) -> VideoInput:
+def _validate_and_trim_duration(video: Input.Video) -> Input.Video:
     """Validates video duration and trims to 5 seconds if needed."""
     duration = video.get_duration()
     _validate_minimum_duration(duration)
@@ -119,7 +116,7 @@ def _validate_minimum_duration(duration: float) -> None:
         raise ValueError("Input video must be at least 5 seconds long.")
 
 
-def _trim_if_too_long(video: VideoInput, duration: float) -> VideoInput:
+def _trim_if_too_long(video: Input.Video, duration: float) -> Input.Video:
     """Trims video to 5 seconds if longer."""
     if duration > 5:
         return trim_video(video, 5)
@@ -241,7 +238,7 @@ class MoonvalleyImg2VideoNode(IO.ComfyNode):
     @classmethod
     async def execute(
         cls,
-        image: torch.Tensor,
+        image: Input.Image,
         prompt: str,
         negative_prompt: str,
         resolution: str,
@@ -362,9 +359,9 @@ class MoonvalleyVideo2VideoNode(IO.ComfyNode):
         prompt: str,
         negative_prompt: str,
         seed: int,
-        video: Optional[VideoInput] = None,
+        video: Input.Video | None = None,
         control_type: str = "Motion Transfer",
-        motion_intensity: Optional[int] = 100,
+        motion_intensity: int | None = 100,
         steps=33,
         prompt_adherence=4.5,
     ) -> IO.NodeOutput:

comfy_api_nodes/nodes_runway.py

@@ -11,12 +11,11 @@ User Guides:
 
 """
 
-from typing import Union, Optional
-from typing_extensions import override
 from enum import Enum
 
-import torch
+from typing_extensions import override
 
+from comfy_api.latest import IO, ComfyExtension, Input, InputImpl
 from comfy_api_nodes.apis import (
     RunwayImageToVideoRequest,
     RunwayImageToVideoResponse,
@@ -44,8 +43,6 @@ from comfy_api_nodes.util import (
     sync_op,
     poll_op,
 )
-from comfy_api.input_impl import VideoFromFile
-from comfy_api.latest import ComfyExtension, IO
 
 PATH_IMAGE_TO_VIDEO = "/proxy/runway/image_to_video"
 PATH_TEXT_TO_IMAGE = "/proxy/runway/text_to_image"
@@ -80,7 +77,7 @@ class RunwayGen3aAspectRatio(str, Enum):
     field_1280_768 = "1280:768"
 
 
-def get_video_url_from_task_status(response: TaskStatusResponse) -> Union[str, None]:
+def get_video_url_from_task_status(response: TaskStatusResponse) -> str | None:
     """Returns the video URL from the task status response if it exists."""
     if hasattr(response, "output") and len(response.output) > 0:
         return response.output[0]
@@ -89,13 +86,13 @@ def get_video_url_from_task_status(response: TaskStatusResponse) -> Union[str, N
 
 def extract_progress_from_task_status(
     response: TaskStatusResponse,
-) -> Union[float, None]:
+) -> float | None:
     if hasattr(response, "progress") and response.progress is not None:
         return response.progress * 100
     return None
 
 
-def get_image_url_from_task_status(response: TaskStatusResponse) -> Union[str, None]:
+def get_image_url_from_task_status(response: TaskStatusResponse) -> str | None:
     """Returns the image URL from the task status response if it exists."""
     if hasattr(response, "output") and len(response.output) > 0:
         return response.output[0]
@@ -103,7 +100,7 @@ def get_image_url_from_task_status(response: TaskStatusResponse) -> Union[str, N
 
 
 async def get_response(
-    cls: type[IO.ComfyNode], task_id: str, estimated_duration: Optional[int] = None
+    cls: type[IO.ComfyNode], task_id: str, estimated_duration: int | None = None
 ) -> TaskStatusResponse:
     """Poll the task status until it is finished then get the response."""
     return await poll_op(
@@ -119,8 +116,8 @@ async def get_response(
 async def generate_video(
     cls: type[IO.ComfyNode],
     request: RunwayImageToVideoRequest,
-    estimated_duration: Optional[int] = None,
-) -> VideoFromFile:
+    estimated_duration: int | None = None,
+) -> InputImpl.VideoFromFile:
     initial_response = await sync_op(
         cls,
         endpoint=ApiEndpoint(path=PATH_IMAGE_TO_VIDEO, method="POST"),
@@ -193,7 +190,7 @@ class RunwayImageToVideoNodeGen3a(IO.ComfyNode):
     async def execute(
         cls,
         prompt: str,
-        start_frame: torch.Tensor,
+        start_frame: Input.Image,
         duration: str,
         ratio: str,
         seed: int,
@@ -283,7 +280,7 @@ class RunwayImageToVideoNodeGen4(IO.ComfyNode):
     async def execute(
         cls,
         prompt: str,
-        start_frame: torch.Tensor,
+        start_frame: Input.Image,
         duration: str,
         ratio: str,
         seed: int,
@@ -381,8 +378,8 @@ class RunwayFirstLastFrameNode(IO.ComfyNode):
     async def execute(
         cls,
         prompt: str,
-        start_frame: torch.Tensor,
-        end_frame: torch.Tensor,
+        start_frame: Input.Image,
+        end_frame: Input.Image,
         duration: str,
         ratio: str,
         seed: int,
@@ -467,7 +464,7 @@ class RunwayTextToImageNode(IO.ComfyNode):
         cls,
         prompt: str,
         ratio: str,
-        reference_image: Optional[torch.Tensor] = None,
+        reference_image: Input.Image | None = None,
     ) -> IO.NodeOutput:
         validate_string(prompt, min_length=1)
 

comfy_api_nodes/nodes_veo2.py

@@ -1,11 +1,9 @@
 import base64
 from io import BytesIO
 
-import torch
 from typing_extensions import override
 
-from comfy_api.input_impl.video_types import VideoFromFile
-from comfy_api.latest import IO, ComfyExtension
+from comfy_api.latest import IO, ComfyExtension, Input, InputImpl
 from comfy_api_nodes.apis.veo_api import (
     VeoGenVidPollRequest,
     VeoGenVidPollResponse,
@@ -232,7 +230,7 @@ class VeoVideoGenerationNode(IO.ComfyNode):
 
             # Check if video is provided as base64 or URL
             if hasattr(video, "bytesBase64Encoded") and video.bytesBase64Encoded:
-                return IO.NodeOutput(VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded))))
+                return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded))))
 
             if hasattr(video, "gcsUri") and video.gcsUri:
                 return IO.NodeOutput(await download_url_to_video_output(video.gcsUri))
@@ -431,8 +429,8 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
         aspect_ratio: str,
         duration: int,
         seed: int,
-        first_frame: torch.Tensor,
-        last_frame: torch.Tensor,
+        first_frame: Input.Image,
+        last_frame: Input.Image,
         model: str,
         generate_audio: bool,
     ):
@@ -493,7 +491,7 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
         if response.videos:
             video = response.videos[0]
             if video.bytesBase64Encoded:
-                return IO.NodeOutput(VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded))))
+                return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded))))
             if video.gcsUri:
                 return IO.NodeOutput(await download_url_to_video_output(video.gcsUri))
             raise Exception("Video returned but no data or URL was provided")

comfy_extras/nodes_video.py

@@ -8,10 +8,7 @@ import json
 from typing import Optional
 from typing_extensions import override
 from fractions import Fraction
-from comfy_api.input import AudioInput, ImageInput, VideoInput
-from comfy_api.input_impl import VideoFromComponents, VideoFromFile
-from comfy_api.util import VideoCodec, VideoComponents, VideoContainer
-from comfy_api.latest import ComfyExtension, io, ui
+from comfy_api.latest import ComfyExtension, io, ui, Input, InputImpl, Types
 from comfy.cli_args import args
 
 class SaveWEBM(io.ComfyNode):
@@ -28,7 +25,6 @@ class SaveWEBM(io.ComfyNode):
                 io.Float.Input("fps", default=24.0, min=0.01, max=1000.0, step=0.01),
                 io.Float.Input("crf", default=32.0, min=0, max=63.0, step=1, tooltip="Higher crf means lower quality with a smaller file size, lower crf means higher quality higher filesize."),
             ],
-            outputs=[],
             hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
             is_output_node=True,
         )
@@ -79,16 +75,15 @@ class SaveVideo(io.ComfyNode):
             inputs=[
                 io.Video.Input("video", tooltip="The video to save."),
                 io.String.Input("filename_prefix", default="video/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."),
-                io.Combo.Input("format", options=VideoContainer.as_input(), default="auto", tooltip="The format to save the video as."),
-                io.Combo.Input("codec", options=VideoCodec.as_input(), default="auto", tooltip="The codec to use for the video."),
+                io.Combo.Input("format", options=Types.VideoContainer.as_input(), default="auto", tooltip="The format to save the video as."),
+                io.Combo.Input("codec", options=Types.VideoCodec.as_input(), default="auto", tooltip="The codec to use for the video."),
             ],
-            outputs=[],
             hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
             is_output_node=True,
         )
 
     @classmethod
-    def execute(cls, video: VideoInput, filename_prefix, format: str, codec) -> io.NodeOutput:
+    def execute(cls, video: Input.Video, filename_prefix, format: str, codec) -> io.NodeOutput:
         width, height = video.get_dimensions()
         full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
             filename_prefix,
@@ -105,10 +100,10 @@ class SaveVideo(io.ComfyNode):
                 metadata["prompt"] = cls.hidden.prompt
             if len(metadata) > 0:
                 saved_metadata = metadata
-        file = f"{filename}_{counter:05}_.{VideoContainer.get_extension(format)}"
+        file = f"{filename}_{counter:05}_.{Types.VideoContainer.get_extension(format)}"
         video.save_to(
             os.path.join(full_output_folder, file),
-            format=VideoContainer(format),
+            format=Types.VideoContainer(format),
             codec=codec,
             metadata=saved_metadata
         )
@@ -135,9 +130,9 @@ class CreateVideo(io.ComfyNode):
         )
 
     @classmethod
-    def execute(cls, images: ImageInput, fps: float, audio: Optional[AudioInput] = None) -> io.NodeOutput:
+    def execute(cls, images: Input.Image, fps: float, audio: Optional[Input.Audio] = None) -> io.NodeOutput:
         return io.NodeOutput(
-            VideoFromComponents(VideoComponents(images=images, audio=audio, frame_rate=Fraction(fps)))
+            InputImpl.VideoFromComponents(Types.VideoComponents(images=images, audio=audio, frame_rate=Fraction(fps)))
         )
 
 class GetVideoComponents(io.ComfyNode):
@@ -159,11 +154,11 @@ class GetVideoComponents(io.ComfyNode):
         )
 
     @classmethod
-    def execute(cls, video: VideoInput) -> io.NodeOutput:
+    def execute(cls, video: Input.Video) -> io.NodeOutput:
         components = video.get_components()
-
         return io.NodeOutput(components.images, components.audio, float(components.frame_rate))
 
+
 class LoadVideo(io.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -185,7 +180,7 @@ class LoadVideo(io.ComfyNode):
     @classmethod
     def execute(cls, file) -> io.NodeOutput:
         video_path = folder_paths.get_annotated_filepath(file)
-        return io.NodeOutput(VideoFromFile(video_path))
+        return io.NodeOutput(InputImpl.VideoFromFile(video_path))
 
     @classmethod
     def fingerprint_inputs(s, file):

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.33.10
-comfyui-workflow-templates==0.7.25
+comfyui-workflow-templates==0.7.51
 comfyui-embedded-docs==0.3.1
 torch
 torchsde