OpenZhenZhen AI 提示词画廊 · SEEDANCE2.5 · video
Asian Wet Market Flood Action
公开作者的 SEEDANCE2.5 视频案例,包含完整 prompt 和可播放成片。

提示词 / Prompt
English prompt
Create a highly cinematic, realistic action sequence inside a crowded traditional Asian wet market during heavy rain and flooding. A young Asian woman with long dark wet hair, wearing a pink waterproof rain suit and black rubber boots, runs rapidly through the narrow market aisles while trying to escape from a massive rushing wave of water behind her. The market is packed with seafood and vegetable stalls, plastic crates, fish tanks, metal counters, hanging tarps, fluorescent ceiling lights, vendors and crowds. The floor is completely flooded with ankle-to-knee-deep dirty rainwater, creating strong reflections and splashes everywhere. Water violently rushes through the market, knocking over crates and flooding the stalls. Start with a close-up tracking shot of the frightened woman looking back over her shoulder while running. Follow her with a fast handheld camera as she runs through the narrow aisle. Use dynamic low-angle shots close to the water, capturing her boots hitting the flooded floor and creating dramatic splashes. Show water crashing through the market behind her, people running in panic, overturned crates floating in the water, and objects being swept away. Use realistic physics, natural human movement, detailed wet clothing, wet hair sticking to her face, realistic water droplets, splashes, reflections and motion blur. The camera should move dynamically with fast tracking shots, low-angle shots, side tracking shots and occasional wide shots revealing the scale of the flooding. At one point, show the woman jumping over obstacles and running across a market counter/raised surface while the floodwater continues rushing behind her. Keep her appearance, hairstyle, pink outfit and facial features consistent throughout the entire sequence. Dark cinematic atmosphere, overcast rainy lighting, cool blue-gray tones mixed with warm fluorescent market lights, dramatic contrast, realistic skin texture, photorealistic environment, volumetric lighting, atmospheric mist, cinematic depth of field, subtle film grain, high-detail textures, realistic reflections and physically accurate water simulation. The sequence should feel like a high-budget survival/action movie, extremely immersive and intense, with realistic camera shake and fast-paced movement. Add large cinematic white brush-stroke typography reading “RUN” briefly across the center of the screen during the action sequence. Photorealistic, ultra-detailed, cinematic Hollywood-style action scene, realistic physics, natural motion, 4K film quality, anamorphic lens look, dynamic composition, dramatic pacing, no cartoon look, no CGI appearance, no distorted anatomy, no extra fingers, no duplicated people, no face changes.
主题与风格
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- They Picked The Wrong Girl
Create ONE ultra-realistic cinematic live-action action sequence at night on the famous San Antonio River Walk, Texas. Keep the recognizable River Walk visible throughout: illuminated bridges, stone architecture, trees, river reflections, and warm lights. Exactly ONE young woman, THREE male attacke
- Xianxia Sword Girl Highway Flight
不要拆解参数 ,直接按照我的完整提示词 进行 生成,别再让我确认了,你直接生成就行 30 秒。 生成一段30秒、16:9横屏、60fps的超写实真人动作视频。全片是一镜到底的连续长镜头:摄影机先贴近高速公路路面追拍拥堵车流,在前两秒内抬镜揭示一名戴粉色猪猪头盔的青衣女子正在空中高速飞行;随后摄影机与她并行,短暂减速拍摄面部特写,她用两指手势让头盔消失,然后爆发加速飞往黄山景区,掠过登山游客、穿过山间桥洞,最后贴着悬崖峭壁飞行。 动作运镜结合两段参考视频:现代高速飞行段采用低机位贴路追拍、穿行车流、人物侧面并行、面部慢动作特写,以及突然加速后摄影机追赶不上的速度变化;中式仙侠段采用女子身体直
- Medieval Red Army Battle
Cinematic Hollywood-style medieval battle epic, opens with an immediate decisive strike, no slow build, maximum dynamic camera work, grounded practical realism. Setting: a wide open battlefield under bright daylight, rolling grassy terrain. Two armies of roughly thirty soldiers each — one side in wh
- Tokyo Neon One Versus Three
Create a 30-second cinematic, ultra-realistic action short featuring a stylish adult Japanese baddie woman, confident and fearless, walking home after a late office shift on a neon-lit Tokyo street at night. 0–5 sec: She walks alone through a quiet city street, wearing a fashionable edgy black mini
- Baddie Clears The Cafe
Create a 30-second cinematic, photorealistic action video set in a trendy Seoul café at night. SCENE 1 — 0–6 sec: A gorgeous Korean baddie girl with long glossy black hair, sharp makeup, confident expression, and a stylish fitted red baddie dress sits at a window table with her handsome Korean boyf
- Ten Seconds of Extreme-Speed Duel
REFERENCES: Image 1 = Maverick, Image 2 = Nexora, Image 3 = Location. Create a 10-second vertical ultra-photorealistic live-action martial-arts fight between Maverick and Nexora in the exact provided location. Preserve both faces, bodies, clothing, chain, and environment consistently. FIGHT — EXTR