infery
← All models

Wan 2.1 VACE Long Reframe

wan-vace-apps-long-reframe

Video generationby Alibaba

Reframe entire videos scene-by-scene using Wan VACE 2.1

Example

Details

Accepts
video

Pricing

Price
10 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility. If None, a random seed is chosen.
shiftnumberShift parameter for video generation.
promptstringThe text prompt to guide video generation. Optional for reframing.
samplerstringenum: unipc, dpm++, eulerSampler to use for video generation.
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
video_urlrequiredstringURL to the source video file. This video will be used as a reference for the reframe task.
paste_backbooleanWhether to paste back the reframed scene to the original video.
resolutionstringenum: auto, 240p, 360p, 480p, 580p, 720pResolution of the generated video.
zoom_factornumberZoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom.
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, 1:1, 9:16Aspect ratio of the generated video.
trim_bordersbooleanWhether to trim borders from the video.
video_qualitystringenum: low, medium, high, maximumThe quality of the generated video.
guidance_scalenumberGuidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.
negative_promptstringNegative prompt for video generation.
scene_thresholdnumberThreshold for scene detection sensitivity (0-100). Lower values detect more scenes.
video_write_modestringenum: fast, balanced, smallThe write mode of the generated video.
return_frames_zipbooleanIf true, also return a ZIP file containing all generated frames.
transparency_modestringenum: content_aware, white, blackThe transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.
interpolator_modelstringenum: rife, filmThe model to use for frame interpolation. Options are 'rife' or 'film'.
num_inference_stepsintegerNumber of inference steps for sampling. Higher values give better quality but take longer.
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.
enable_auto_downsamplebooleanWhether to enable auto downsample.
auto_downsample_min_fpsnumberMinimum FPS for auto downsample.

Output

FieldTypeDescription
videoThe output video file.