Wan2TextToVideoApi - ComfyUI Built-in Node Documentation

This node generates a video from a text description using the Wan 2.7 model.

This node generates a video from a text description using the Wan 2.7 model. It sends your prompt to the Wan video-generation API, waits for the task to finish, and returns the resulting video. You can optionally connect an audio clip to influence the video’s motion and timing; if no audio is provided, the model automatically generates matching audio.

Inputs

Common Inputs

These inputs are always available at the top level of the node.

Parameter	Description	Data Type	Required	Range
model	The specific model to use for video generation.	DYNAMIC_COMBO	Yes	"wan2.7-t2v"
audio	Audio for driving video generation (e.g., lip sync, beat-matched motion). Duration: 3s-30s. If not provided, the model automatically generates matching background music or sound effects.	AUDIO	No	-
seed	Seed to use for generation (default: 0).	INT	Yes	0 to 2147483647
prompt_extend	Whether to enhance the prompt with AI assistance (default: True).	BOOLEAN	Yes	True False
watermark	Whether to add an AI-generated watermark to the result (default: False).	BOOLEAN	Yes	True False

wan2.7-t2v Inputs

These settings appear when the wan2.7-t2v model is selected.

Parameter	Description	Data Type	Required	Range
prompt	Prompt describing the elements and visual features. Supports English and Chinese.	STRING	Yes	-
negative_prompt	Negative prompt describing what to avoid. Default is an empty string.	STRING	No	-
resolution	The resolution of the output video.	COMBO	Yes	"720P" "1080P"
ratio	The aspect ratio of the output video.	COMBO	Yes	"16:9" "9:16" "1:1" "4:3" "3:4"
duration	The length of the video in seconds (default: 5).	INT	Yes	2 to 15

Note: The prompt input must not be empty. The audio input is optional; if provided, the node accepts audio between 1.5 and 60 seconds, even though the tooltip recommends 3s-30s. If no audio is supplied, the model automatically generates matching audio. When negative_prompt is left empty, it is not sent to the API. prompt_extend and watermark are advanced options.

Outputs

Output Name	Description	Data Type
output	The generated video file.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 2b35fb3e897f8c5fb9786576f4e314cb6709527a3cdc4f2eb9f0600d09076835