Video to Video — 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.

≈ 179.243 kredi/sn

Ayarlar

Video Urlzorunlu

URL of the source video whose motion and framing drive the generation.

Image Urlzorunlu

URL of the restyled first frame. The video is regenerated in this frame's identity/style.

Keyframesisteğe bağlı

Optional restyled keyframes pinned at specific output frame indices to anchor identity over long videos.

Resolutionisteğe bağlı

Output resolution tier. Orientation follows the source video (720p is 1280x720 or 720x1280; 480p is 832x480 or 480x832).

Num Framesisteğe bağlı

Maximum number of output frames. Capped at the source video's frame count.

Segmentation Promptisteğe bağlı

Text prompt for SAM-3 subject segmentation. The segmented subject's pixels condition the generation; the rest of the frame is regenerated freely.

Num Inference Stepsisteğe bağlı

Number of diffusion sampling steps per clip. Higher improves quality but is slower.

Guidance Scaleisteğe bağlı

Classifier-free guidance scale. Controls prompt adherence versus creativity.

Vace Scaleisteğe bağlı

VACE conditioning scale. Controls how strongly the source video's structure constrains the generation.

Seedisteğe bağlı

Random seed for reproducibility. The same seed is used for every clip of a multi-clip generation.

Enable Safety Checkeristeğe bağlı

Enable safety checking of inputs and outputs.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap