WanTextToVideoApi - ComfyUI Built-in Node Documentation

Complete documentation for the WanTextToVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage.

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

The Wan Text to Video node generates video content based on text descriptions. It uses AI models to create videos from prompts and supports various video sizes, durations, and optional audio inputs. The node can automatically generate audio when needed and provides options for prompt enhancement and watermarking.

Inputs

Parameter	Data Type	Required	Range	Description
model	COMBO	Yes	”wan2.5-t2v-preview" "wan2.6-t2v”	Model to use (default: “wan2.6-t2v”)
prompt	STRING	Yes	-	Prompt describing the elements and visual features. Supports English and Chinese (default: "")
negative_prompt	STRING	No	-	Negative prompt describing what to avoid (default: "")
size	COMBO	No	”480p: 1:1 (624x624)" "480p: 16:9 (832x480)" "480p: 9:16 (480x832)" "720p: 1:1 (960x960)" "720p: 16:9 (1280x720)" "720p: 9:16 (720x1280)" "720p: 4:3 (1088x832)" "720p: 3:4 (832x1088)" "1080p: 1:1 (1440x1440)" "1080p: 16:9 (1920x1080)" "1080p: 9:16 (1080x1920)" "1080p: 4:3 (1632x1248)" "1080p: 3:4 (1248x1632)“	Video resolution and aspect ratio (default: “720p: 1:1 (960x960)“)
duration	INT	No	5-15 (in steps of 5)	Duration of the video in seconds. A 15-second duration is available only for the Wan 2.6 model (default: 5)
audio	AUDIO	No	-	Audio must contain a clear, loud voice, without extraneous noise or background music
seed	INT	No	0-2147483647	Seed to use for generation (default: 0)
generate_audio	BOOLEAN	No	-	If no audio input is provided, generate audio automatically (default: False)
prompt_extend	BOOLEAN	No	-	Whether to enhance the prompt with AI assistance (default: True)
watermark	BOOLEAN	No	-	Whether to add an AI-generated watermark to the result (default: False)
shot_type	COMBO	No	”single" "multi”	Specifies the shot type for the generated video, that is, whether the video is a single continuous shot or multiple shots with cuts. This parameter takes effect only when prompt_extend is True (default: “single”)

Note: The Wan 2.6 model does not support 480p resolutions. A 15-second duration is only supported by the Wan 2.6 model. When providing audio input, it must be between 3.0 and 29.0 seconds in duration and contain clear voice without background noise or music.

Outputs

Output Name	Data Type	Description
output	VIDEO	The generated video based on the input parameters

---

Source fingerprint (SHA-256): 4fbdb2e06ff15849684de860ca3fdf4eb43e6af1803483b4baa7229e584f6e25