ComfyUI Node Runs on cloud
Wan Text to Video
Generates a video based on a text prompt.
Wan Text to Video
- audio
- VIDEO
◄modelwan2.6-t2v►
◄prompt►
◄negative_prompt►
◄size720p: 1:1 (960x960)►
◄duration5►
◄seed0►
◄generate_audiofalse►
◄prompt_extendtrue►
◄watermarkfalse►
◄shot_type▾►
Categorypartner/video/Wan
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | wan2.6-t2v | Model to use. |
| prompt | STRING | Prompt describing the elements and visual features. Supports English and Chinese. | |
| negative_promptopt | STRING | Negative prompt describing what to avoid. | |
| sizeopt | COMBO | 720p: 1:1 (960x960) | 13 options: 480p: 1:1 (624x624), 480p: 16:9 (832x480), 480p: 9:16 (480x832), 720p: 1:1 (960x960), 720p: 16:9 (1280x720), 720p: 9:16 (720x1280), +7 |
| durationopt | INT | 55–15 | A 15-second duration is available only for the Wan 2.6 model. |
| audioopt | AUDIO | Audio must contain a clear, loud voice, without extraneous noise or background music. | |
| seedopt | INT | 00–2147483647 | Seed to use for generation. |
| generate_audioopt | BOOLEAN | false | If no audio input is provided, generate audio automatically. |
| prompt_extendopt | BOOLEAN | true | Whether to enhance the prompt with AI assistance. |
| watermarkopt | BOOLEAN | false | Whether to add an AI-generated watermark to the result. |
| shot_typeopt | COMBO | 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. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| VIDEO | VIDEO | — |