infery
← All models

Wan VACE Video Edit

wan-vace-apps-video-edit

Video generationby Alibaba

Edit videos using plain language and Wan VACE

Example

Details

Accepts
video + image

Pricing

Price
12.5 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
promptrequiredstringPrompt to edit the video.
video_urlrequiredstringURL of the input video.
image_urlsarrayURLs of the input images to use as a reference for the generation.
resolutionstringenum: auto, 240p, 360p, 480p, 580p, 720pResolution of the edited video.
video_typestringenum: auto, general, humanThe type of video you're editing. Use 'general' for most videos, and 'human' for videos emphasizing human subjects and motions. The default value 'auto' means the model will guess based on the first frame of the video.
accelerationAcceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.
aspect_ratiostringenum: auto, 16:9, 9:16, 1:1Aspect ratio of the edited video.
return_frames_zipbooleanWhether to include a ZIP archive containing all generated frames.
enable_safety_checkerbooleanWhether to enable the safety checker.
enable_auto_downsamplebooleanWhether to enable automatic downsampling. If your video has a high frame rate or is long, enabling longer sequences to be generated. The video will be interpolated back to the original frame rate after generation.
auto_downsample_min_fpsnumberThe minimum frames per second to downsample the video to.

Output

FieldTypeDescription
videoThe edited video.
frames_zipZIP archive of generated frames if requested.