Pixverse C1 Text-to-Video
PixVerse C1 generates film-grade videos from text prompts with flexible duration (1-15s), multiple resolutions up to 1080p, and optional native audio generation.
示例
A charismatic street magician in a worn velvet coat performs on a rainy Paris sidewalk at dusk. A small crowd watches as he produces a glowing golden coin from thin air. A skeptical little girl pushes to the front, arms crossed. He crouches to her level, winks, then reaches behind her ear - pulling out not a coin, but a tiny living butterfly. The girl's expression melts from suspicion into pure awe. Shallow depth of field, warm bokeh lights, slow-motion butterfly release, cinematic.
试试这条提示词 →A young woman in a soaked trench coat sprints through a rain-drenched neon-lit alley in Tokyo, glancing back in terror. Reflections of red and blue signage ripple across the puddles beneath her feet. A shadowy figure in a hood rounds the corner behind her. She skids to a stop at a dead end, turns, and pulls a small glowing device from her pocket - her expression shifting from fear to cold determination. Cinematic handheld camera, motion blur, dramatic shadows, 4K.
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。