> ## Documentation Index > Fetch the complete documentation index at: https://docs.comfy.org/llms.txt > Use this file to discover all available pages before exploring further. # Kling Start-End Frame to Video - ComfyUI Built-in Node > A node that creates smooth video transitions between start and end frames using Kling's AI technology ComfyUI Built-in Kling Start-End Frame to Video Node The Kling Start-End Frame to Video node lets you create smooth video transitions between two images. It automatically generates all the intermediate frames to produce a fluid transformation. ## Parameters ### Required Parameters | Parameter | Type | Description | | ---------------- | ------ | ----------------------------------------------- | | start\_frame | Image | Starting image for the video | | end\_frame | Image | Ending image for the video | | prompt | String | Text describing video content and transition | | negative\_prompt | String | Elements to avoid in the video | | cfg\_scale | Float | Controls how closely to follow the prompt | | aspect\_ratio | Select | Output video aspect ratio | | mode | Select | Video generation settings (mode/duration/model) | ### Mode Options Available mode combinations: * standard mode / 5s duration / kling-v1 * standard mode / 5s duration / kling-v1-5 * pro mode / 5s duration / kling-v1 * pro mode / 5s duration / kling-v1-5 * pro mode / 5s duration / kling-v1-6 * pro mode / 10s duration / kling-v1-5 * pro mode / 10s duration / kling-v1-6 Default: "pro mode / 5s duration / kling-v1" ### Output | Output | Type | Description | | ------ | ----- | --------------- | | VIDEO | Video | Generated video | ## How It Works The node analyzes the start and end frames to create a smooth transition sequence between them. It sends the images and parameters to Kling's API server, which generates all necessary intermediate frames for a fluid transformation. The transition style and content can be guided using prompts, while negative prompts help avoid unwanted elements. ## Source Code \[Node Source Code (Updated 2025-05-03)] ```python theme={null} class KlingStartEndFrameNode(KlingImage2VideoNode): """ Kling First Last Frame Node. This node allows creation of a video from a first and last frame. It calls the normal image to video endpoint, but only allows the subset of input options that support the `image_tail` request field. """ @staticmethod def get_mode_string_mapping() -> dict[str, tuple[str, str, str]]: """ Returns a mapping of mode strings to their corresponding (mode, duration, model_name) tuples. Only includes config combos that support the `image_tail` request field. """ return { "standard mode / 5s duration / kling-v1": ("std", "5", "kling-v1"), "standard mode / 5s duration / kling-v1-5": ("std", "5", "kling-v1-5"), "pro mode / 5s duration / kling-v1": ("pro", "5", "kling-v1"), "pro mode / 5s duration / kling-v1-5": ("pro", "5", "kling-v1-5"), "pro mode / 5s duration / kling-v1-6": ("pro", "5", "kling-v1-6"), "pro mode / 10s duration / kling-v1-5": ("pro", "10", "kling-v1-5"), "pro mode / 10s duration / kling-v1-6": ("pro", "10", "kling-v1-6"), } @classmethod def INPUT_TYPES(s): modes = list(KlingStartEndFrameNode.get_mode_string_mapping().keys()) return { "required": { "start_frame": model_field_to_node_input( IO.IMAGE, KlingImage2VideoRequest, "image" ), "end_frame": model_field_to_node_input( IO.IMAGE, KlingImage2VideoRequest, "image_tail" ), "prompt": model_field_to_node_input( IO.STRING, KlingImage2VideoRequest, "prompt", multiline=True ), "negative_prompt": model_field_to_node_input( IO.STRING, KlingImage2VideoRequest, "negative_prompt", multiline=True, ), "cfg_scale": model_field_to_node_input( IO.FLOAT, KlingImage2VideoRequest, "cfg_scale" ), "aspect_ratio": model_field_to_node_input( IO.COMBO, KlingImage2VideoRequest, "aspect_ratio", enum_type=AspectRatio, ), "mode": ( modes, { "default": modes[2], "tooltip": "The configuration to use for the video generation following the format: mode / duration / model_name.", }, ), }, "hidden": {"auth_token": "AUTH_TOKEN_COMFY_ORG"}, } DESCRIPTION = "Generate a video sequence that transitions between your provided start and end images. The node creates all frames in between, producing a smooth transformation from the first frame to the last." def parse_inputs_from_mode(self, mode: str) -> tuple[str, str, str]: """Parses the mode input into a tuple of (model_name, duration, mode).""" return KlingStartEndFrameNode.get_mode_string_mapping()[mode] def api_call( self, start_frame: torch.Tensor, end_frame: torch.Tensor, prompt: str, negative_prompt: str, cfg_scale: float, aspect_ratio: str, mode: str, auth_token: Optional[str] = None, ): mode, duration, model_name = self.parse_inputs_from_mode(mode) return super().api_call( prompt=prompt, negative_prompt=negative_prompt, model_name=model_name, start_frame=start_frame, cfg_scale=cfg_scale, mode=mode, aspect_ratio=aspect_ratio, duration=duration, end_frame=end_frame, auth_token=auth_token, ) ```