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.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe Wan2VideoEditApi node uses the Wan 2.7 model to edit a video based on text instructions, reference images, or style transfer. It processes the input video and generates a new video according to the specified parameters like resolution, duration, and aspect ratio.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
model | COMBO | Yes | "wan2.7-videoedit" | The model to use for video editing. |
model.prompt | STRING | Yes | - | Editing instructions or style transfer requirements. (default: empty string) |
model.resolution | COMBO | Yes | "720P""1080P" | The resolution for the output video. |
model.ratio | COMBO | Yes | "16:9""9:16""1:1""4:3""3:4" | The aspect ratio for the output video. If not changed, it approximates the input video’s ratio. |
model.duration | COMBO | Yes | "auto""2""3""4""5""6""7""8""9""10" | The output duration in seconds. ‘auto’ matches the input video duration. A specific value truncates from the start of the video. (default: “auto”) |
model.reference_images | IMAGE | No | - | A list of up to 4 reference images to guide the edit. |
video | VIDEO | Yes | - | The video to edit. |
seed | INT | No | 0 to 2147483647 | The seed to use for generation. (default: 0) |
audio_setting | COMBO | No | "auto""origin" | ’auto’: model decides whether to regenerate audio based on the prompt. ‘origin’: preserve the original audio from the input video. (default: “auto”) |
watermark | BOOLEAN | No | - | Whether to add an AI-generated watermark to the result. (default: False) |
- The
model.promptmust be at least 1 character long. - The input
videomust be between 2 and 10 seconds in duration. - The
model.reference_imagesinput can accept a maximum of 4 images.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
output | VIDEO | The edited video generated by the model. |
Source fingerprint (SHA-256):
1ea6cacbf8f5b6666e164c4806d931d21ddd44568e5c9f6d44f389288f5ce84f