Image to Video · Text to Video — Turn up to five reference images into one continuous, consistent video with Bernini-R, with smooth, stable camera motion and no scene cuts.

≈ 71.697 kredi/sn

Ayarlar

Reference Image Urlszorunlu

Reference subject image(s); up to 5.

Negative Promptisteğe bağlı

Negative prompt. Defaults to the standard Wan2.2 negative prompt.

Num Inference Stepsisteğe bağlı

Number of denoising steps.

Max Image Sizeisteğe bağlı

Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.

Seedisteğe bağlı

Seed for reproducibility. Random when omitted.

Enable Prompt Expansionisteğe bağlı

Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.

Num Framesisteğe bağlı

Number of frames. Snapped internally to 4k+1.

Frames Per Secondisteğe bağlı

Output frames per second.

Accelerationisteğe bağlı

Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.

Aspect Ratioisteğe bağlı

Output aspect ratio.

Enable Safety Checkeristeğe bağlı

Authorized callers may set false to request relaxed screening.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap