Image to Video — Expressive facial performance, natural speech-expression coordination, realistic body motion, and accurate audio-video synchronization with DaVinci-MagiHuman model

≈ 44.811 kredi/sn

Ayarlar

Image Urlzorunlu

URL of the reference image for image-to-video generation.

Audio Urlisteğe bağlı

Optional URL of the driving audio for lipsync mode. If omitted, audio is generated from the prompt.

Durationisteğe bağlı

Duration of the generated video in seconds.

Resolutionisteğe bağlı

Output resolution. '256p' uses the official base-model 448x256 path. '1080p' uses the official base + 1080p super-resolution pipeline. '540p' and '720p' reuse that sharper 1080p SR path and downsample to the requested output size.

Num Inference Stepsisteğe bağlı

Number of denoising steps. Defaults to 8 for 256p and 32 for 540p/720p/1080p (base + SR).

Guidance Scaleisteğe bağlı

Classifier-free guidance scale.

Seedisteğe bağlı

Random seed for reproducibility.

Enable Safety Checkeristeğe bağlı

If enabled, runs safety checks on the prompt and input image.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap