提示

Starting from the provided photo, generate a short realistic video of the person in the image. The person appears slightly confused and puzzled, as if they don’t fully understand what has just been said to them. Their facial expression changes subtly: eyebrows slightly raised, a brief pause, a small head tilt, and a look of mild disbelief. After a moment of hesitation, the person moves their lips naturally and says, in a confused and genuine tone: “E che significa?” The movement should be natural and realistic, with soft head motion and minimal body movement. Lighting remains consistent with the original photo, background unchanged. Style: realistic, cinematic, shallow depth of field, smooth facial animation, natural blinking, no exaggeration.

video

Starting from the provided photo, generate a short realistic video of the person in the image. The person appears sli...

Sora 2video:sora2-image-to-video-standard圖片轉影片
Jan 24, 2026, 01:26 AM

設定

提供者
Sora 2
模型
video:sora2-image-to-video-standard
已創建
Jan 24, 2026, 01:26 AM
製作人員名單
20
模式
圖片轉影片
長寬比
16:9
參考圖片
參考圖片 1

創建相似的東西

下面的生成器會預先選擇用於此記錄的模型,讓你可以更快地混合這個想法。

提交後,新任務將出現在此。