OpenZhenZhen AI 提示词画廊 · SEEDANCE2.5 · video

Ultra-Realistic Sushi Chef Macro

公开作者的 SEEDANCE2.5 视频案例,包含完整 prompt 和可播放成片。

Ultra-Realistic Sushi Chef Macro — AI video creation
Ultra-Realistic Sushi Chef Macro

提示词 / Prompt

English prompt

One continuous 15-second take. No cuts. No scene changes. No transitions. PREMISE: An experienced sushi chef prepares a single piece of salmon nigiri from start to finish. The purpose of this scene is to demonstrate extremely realistic hand movement, knife physics, food texture, reflections, cloth simulation, and shallow depth of field. The entire clip happens in one take. SUBJECT: Professional sushi chef. Late 40s. Ordinary appearance. White chef jacket. Dark blue apron. Natural hands with wrinkles, veins, fingernails, tiny scars from years of cooking. Nothing should feel stylized. Everything should feel documentary. CAMERA: ARRI Alexa 35. 100mm macro lens. Locked handheld. Tiny natural breathing movement only. No zoom. No reframing. No focus hunting. Focus stays perfectly on the hands. BACKGROUND: Minimal Japanese sushi bar. Warm wood counter. Everything behind the chef dissolves into creamy bokeh. No distractions. ACTION: 0–3s The chef picks up a fresh piece of salmon. The fish bends naturally under gravity. Its surface catches the light with realistic moisture. The knife is already in his other hand. 3–6s He slices the salmon in one continuous motion. The blade glides effortlessly. The salmon compresses slightly before separating. Tiny fibers stretch realistically before releasing. The knife reflects the environment accurately. 6–9s He shapes a piece of sushi rice using both hands. Individual rice grains compress together. A few grains shift naturally under finger pressure. Nothing sticks unnaturally. 9–12s The salmon is placed over the rice. His thumb gently presses the top. The fish conforms around the rice naturally. Tiny surface reflections move as it bends. 12–15s He brushes a thin layer of soy glaze across the salmon. The glaze catches highlights. The brush leaves tiny streaks before leveling naturally. The finished nigiri is placed onto a black ceramic plate. The plate rotates slightly. Steam from fresh rice remains subtly visible. AUDIO: Only real restaurant ambience. Knife on cutting board. Soft cloth movement. Tiny brush sounds. Hands touching rice. No music. No narration. No dialogue. RENDER: Photorealistic. Natural color science. Fine film grain. Realistic food texture. Physically accurate reflections. Natural hand anatomy. Correct knife reflections. Perfect temporal consistency. NEGATIVE: No extra fingers. No morphing. No floating rice. No unrealistic knife motion. No CGI look. No oversaturated colors. No text. No logos. No overlays. Everything should look indistinguishable from a high-end food documentary.

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

  • 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