infery
← All models

ID-V2V

id-v2v

Video editby ID V2v

Restyle a video’s scene, lighting, and visual style from edited keyframes while preserving the source subjects’ identity, expressions, gaze, and motion. Developed by Eyeline Labs and Netflix researchers.

Example

Details

Accepts
image + video

Pricing

Price
25 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility. The same seed is used for every clip of a multi-clip generation.
promptrequiredstringThe prompt describing the restyled video to generate.
image_urlrequiredstringURL of the restyled first frame. The video is regenerated in this frame's identity/style.
keyframesarrayOptional restyled keyframes pinned at specific output frame indices to anchor identity over long videos.
video_urlrequiredstringURL of the source video whose motion and framing drive the generation.
num_framesintegerMaximum number of output frames. Capped at the source video's frame count.
resolutionstringenum: 480p, 720pOutput resolution tier. Orientation follows the source video (720p is 1280x720 or 720x1280; 480p is 832x480 or 480x832).
vace_scalenumberVACE conditioning scale. Controls how strongly the source video's structure constrains the generation.
guidance_scalenumberClassifier-free guidance scale. Controls prompt adherence versus creativity.
num_inference_stepsintegerNumber of diffusion sampling steps per clip. Higher improves quality but is slower.
segmentation_promptstringText prompt for SAM-3 subject segmentation. The segmented subject's pixels condition the generation; the rest of the frame is regenerated freely.
enable_safety_checkerbooleanEnable safety checking of inputs and outputs.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.