Ovi Image-to-Video
Ovi is a Veo-3-like image-to-video model that generates synchronized video and audio from text or text+image prompts.
示例
Bright evenly lit laboratory room with metallic walls and soft white light reflections. A human man in a suit stands face-to-face with a humanoid robot, both in perfect focus. Camera: static medium close-up, centered framing, high exposure with clear details on both faces. Mood: tense, thoughtful, futuristic. <S>We built you to understand us.<E> A Sign <S>But sometimes I wonder if you understand us too well.<E> The robot tilts its head slightly, eyes glowing faint blue, voice calm and precise. <S>Understanding is not the same as becoming.<E> <AUDCAP>Soft ambient hum of el
试试这条提示词 →A 5-second, dynamic close-up of a sleek, advanced android's head and upper torso. Its armored plates are etched with neon circuit patterns that pulse with a soft blue light. Its face is a polished metal and dark glass visor. As it boots up, its articulated jaw and vocal synthesizer move with precise, mechanical motion to form the words. Mood: Technological, mysterious, and immersive. <S>System. Online.<E> <AUDCAP>The clear, synthetic voice of the android, the low hum of its internal systems, and the faint, distant sound of hovering vehicles and city rain.<ENDAUDCAP>
试试这条提示词 →规格
相似模型
全部模型 →价格按每次生成计算,仅在生成成功时从余额扣款。生成失败会自动退款。示例展示的是模型的能力;实际结果取决于你的提示词和设置。