Person Character影片提示詞

Young Aveline stands beside her massive black dragon on the mountain landscape. The dragon suddenly raises and slowly spreads its enormous dark wings to their full span, powerful and majestic. Wind rushes outward from the movement, blowing Aveline’s...

Create a 20-second ultra-realistic cinematic camping vlog featuring a young Japanese woman with straight black hair and bangs, wearing a dusty pink outdoor jacket. Scene 1 (0–4 sec): Selfie-style vlog in a beautiful pine forest during golden hour. She smiles at the camera while holding a beige tent bag and excitedly introduces her solo camping adventure. Natural handheld camera movement, realistic facial expressions. Scene 2 (4–7 sec): Wide cinematic shot of her setting up a beige camping tent among tall pine trees. She happily raises both hands to celebrate after pitching the tent. Warm sunlight filters through the forest. Scene 3 (7–12 sec): Nighttime campfire scene. She sits on a folding camping chair, roasting a marshmallow on a stick. Close-up of her gently blowing on the toasted marshmallow, with realistic firelight illuminating her face. Scene 4 (12–16 sec): She sits beside the campfire holding a glowing marshmallow, enjoying the peaceful night in the forest. Natural expressions, cozy atmosphere, realistic shadows and warm orange lighting. Scene 5 (16–20 sec): Inside her illuminated tent at night, she smiles at the camera while holding a camping lantern. Suddenly, she hears a mysterious noise outside, opens her eyes wide, and pulls her sleeping bag up to her nose with a cute, surprised expression. Visual style: Photorealistic live-action, 4K, cinematic depth of field, natural skin texture, realistic lighting, smooth camera transitions, authentic outdoor atmosphere, detailed facial expressions, cozy solo camping aesthetic. Audio: Natural forest ambience, birds chirping, gentle wind, crackling campfire, subtle fabric sounds, and soft nighttime forest ambience. No background music, no subtitles, no text, no watermark. Consistency: Maintain exactly the same woman, hairstyle, outfit, facial features, and tent throughout all scenes.

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and loose casual pants, carrying a simple canvas shoulder bag. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Quiet older Seoul neighborhood on a pleasant morning. Narrow residential street with low-rise apartment buildings, small local shops, parked bicycles, potted plants and modest storefronts. A little Korean girl, around 5–6 years old, is standing safely near the sidewalk with a small ice cream cone in one hand. Her shoelaces have come completely undone. Lighting & Atmosphere: Warm, cheerful and cozy morning atmosphere. Soft sunlight filters between the buildings, creating gentle warm highlights while some areas remain naturally shaded. Muted surroundings, soft shadows, slightly faded colors and a nostalgic early-2000s feeling. The scene should feel wholesome and ordinary rather than sentimental or cinematic. Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person casually walking with her. Multi-shot but completely candid and unstaged. Natural handheld movement, subtle camera shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle digital noise and natural microphone noise. Shot 1 — 00:00–00:04: Medium-wide handheld shot as the young woman walks casually down the quiet street. She notices a little girl standing near the sidewalk, holding an ice cream cone while looking down at her untied shoelaces with a confused expression. Shot 2 — 00:04–00:07: The camera moves slightly closer as the woman slows down. The little girl looks at her shoelaces, then at her ice cream, clearly unsure how to deal with both at once. The woman understands the problem and gently gestures toward the laces, asking if she can help. Shot 3 — 00:07–00:11: The woman crouches down beside the child and carefully ties the loose shoelaces into a secure bow while the child stands still, carefully holding her ice cream away from them. The woman's movements are gentle and efficient. Shot 4 — 00:11–00:14: She gives the finished shoelaces a quick little check and stands back up. The child looks down at her shoes, then looks up at the woman with a small grateful smile. Shot 5 — 00:14–00:17: The woman gives the child a warm little smile and a tiny nod, then continues walking down the street. The child happily takes another bite of her ice cream. Shot 6 — 00:17–00:20: As the woman walks away, she briefly turns toward the camcorder and gives a quiet, contented smile before looking forward again and continuing down the street. Audio: Natural sound only—soft footsteps, distant traffic, subtle neighborhood ambience, children's distant voices, light breeze, fabric movement and the natural sounds of the street.

ai video field test (oct 1, 2026) seedance 2.5, 1080p prompt: Create a 30-second ultra-photorealistic live-action personal vlog / home-video style film of an elderly Korean man spending a quiet ordinary summer morning in South Korea. The result should feel like a forgotten personal recording of an ordinary summer day. Not a commercial. Not a fashion film. Not a music video. Not a professional cinematic production. It should feel like someone casually captured pieces of a real morning as it happened. The emotional appeal should come from small human moments: waking up slowly, sitting on the edge of the bed, rubbing his face, putting on slippers, walking through a modest apartment, making a simple breakfast, standing quietly in the kitchen, looking out the window, and stepping outside into familiar neighborhood streets. The feeling should be quiet, masculine, nostalgic, slightly melancholic, warm, spontaneous, and deeply human. Set it in a real Korean neighborhood — modest apartment interiors, summer light, a small kitchen, quiet residential streets, low-rise buildings, local storefronts, alleyways, electric fans, sliding windows, convenience stores, crosswalk sounds, distant traffic, and subtle signs of daily life in Korea. Keep the environment grounded and unglamorous, like a normal lived-in morning. The man should feel completely real: an elderly Korean man, late 60s to 70s, ordinary appearance, gentle face, natural aging, slightly tired but calm presence, simple casual home clothes, believable posture and movement. Maintain consistent identity throughout the video. Visual style: Modern but humble handheld home-video / smartphone footage with imperfect framing, natural camera shake, slight autofocus breathing, occasional exposure shifts, and subtle observational composition. Nothing polished or overly cinematic. The camera should feel like it just happened to be there. Mood and tone: Natural, intimate, and observational. Slightly melancholic but not dramatic. Warm summer air, soft ambient light, a sense of memory and passing time. The tone should feel personal and truthful. Suggested sequence: Slowly waking up in bed in the morning heat Sitting up and gathering himself Walking to the kitchen in slippers Pouring cereal or preparing a very simple breakfast Standing quietly in the kitchen eating or drinking Looking out the window for a moment Leaving home and stepping into the neighborhood Walking slowly through familiar Korean side streets Audio: Use natural diegetic sound only — room tone, bedsheets, slippers on the floor, spoon against bowl, fridge hum, fan noise, distant traffic, birds, footsteps, quiet street ambience, a passing scooter, crosswalk beeps, neighborhood sounds. No music, no narration, no subtitles, no logos, no watermark. Important constraints: Prioritize natural behavior, consistent identity, believable physics, imperfect handheld framing, authentic environmental details, and the feeling that the camera happened to be there.

Create a 30-second ultra-realistic AAA open-world third-person action game mission, fully rendered as authentic GTA-style gameplay from beginning to end. Generate the female player character yourself: a stylish young woman with long dark hair, dark fitted jacket, dark pants and practical boots, keeping her appearance perfectly consistent throughout. Set the mission at a massive modern cargo ship at night, surrounded by dark ocean, shipping containers, cranes, realistic water, rain and distant city lights. Use a true third-person gameplay camera, realistic game physics, detailed game-engine graphics and a complete GTA-style HUD with minimap, mission objectives and notifications. At 0–4 seconds, the character quietly climbs onto the cargo ship and the HUD shows MISSION START — CARGO SHIP — FIND THE PACKAGE. At 4–9 seconds, she moves between stacked containers while avoiding security guards and reaches the marked container; HUD changes to CONTAINER LOCATED. At 9–14 seconds, she opens the container, retrieves a mysterious package and the HUD shows PACKAGE SECURED. At 14–18 seconds, an alarm suddenly activates, red warning lights flash and security begins searching the ship; HUD changes to ALARM TRIGGERED — ESCAPE. At 18–24 seconds, she runs through the container area toward the edge of the ship while security follows, then reaches a waiting speedboat below. At 24–27 seconds, she jumps into the speedboat and rapidly drives away across the ocean as the cargo ship recedes behind her. At 27 seconds, make exactly one hard cut to a natural third-person gameplay continuation showing her speedboat racing toward distant city lights, with the HUD displaying MISSION PASSED — PACKAGE SECURED — ESCAPE SUCCESSFUL — RANK S. Make the entire video look like high-budget GTA gameplay, including authentic HUD, minimap, NPC behavior, camera movement, water physics, vehicle physics, lighting and reflections. No live-action look, anime, cartoon, random cuts, teleportation or graphic gore.

Italian amphitheater, tour guide to camera: “Qui cantavano migliaia di persone.”

animate golden ratios and mandlebrot sets, sacred geometry and cymatics in a well thought out eye candy javascript or 3js 3d animated video. use motion animation to show off your skills and push the limits with quick cuts, vibrant colors and cute but badass characters. make it like an adult cartoon you'd watch on adult swim

クラウドのLinux環境にBlenderをPythonモジュールとして入れ、シーン構築からレンダーまで全部スクリプトで実行 ステージ、照明、紙吹雪、カメラワークをコードで組み、Cyclesで描画 グロー、フラッシュ、色収差の後処理とMP4化まで自動 BGMもサンプル素材なし。キック、スネア、ベース、シンセをnumpyのコードで合成 ダンスの腰の高さを解析し、本来のテンポが約137BPMと特定 拍ごとにダンスの時間を補正して、全拍で沈み込みがキックと±0.5フレームで一致 カット、照明、ズーム、質感の切り替えもすべて拍の頭に合わせ、最後の一撃で全員静止 カメラはPythonで毎フレーム計算。急降下、回り込み、顔のアップから横に振り抜くカットなど 拍の頭でクローム、ゴールド、ホログラム、ボクセルに質感とメッシュが変わる

Create an ultra-realistic Korean zombie-horror sequence inside an old apartment elevator at night. A woman in a long golden light-cream one-piece dress enters alone, carrying a shopping bag. The elevator stops between floors, the lights flicker, and the floor indicator glitches to 13. A dark figure appears only in the mirror, whose reflection slowly becomes infected with pale skin, milky eyes, and dark veins. The mirror cracks as an infected hand reaches through. The doors open to a nonexistent dark floor where infected silhouettes rush toward her. She barely escapes as the doors slam shut. When the elevator reaches the 12th floor, she exits—but her reflection stays behind, smiles, then suddenly lunges toward the camera. Cut to black. Style: Ultra-realistic Korean zombie horror, claustrophobic elevator, cinematic handheld camera, flickering fluorescent lights, photorealistic skin, realistic reflections, tense atmosphere, dark shadows, natural facial expressions. Negative prompt: Cartoon, anime, stylized CGI, exaggerated gore, distorted anatomy, extra limbs, inconsistent face, unrealistic reflections, floating objects, text, subtitles, watermark.

Knight fighting many black bats dragon lands standing over knight blasts black bats with fire

电影级写实质感，纯古风中国仙侠美学。 以成熟的身份冲突、克制的武侠人物表演、依靠潜台词和人物站位完成反转的资深编剧式对白为核心。 采用： Arri Alexa 电影机质感 自然体积光 细腻胶片颗粒 核心反转 这次跳出以下这些已经使用过的结构： 抗命 替罪 认输 营救 忠诚测试 把冲突直接放在 “继承” 本身。 所有人都认为： 对小师妹最大的认可，就是让她接过剑仙师姐的剑、名号和位置。 真正的反转却是—— 师姐恰恰因为真正认可她，才不允许她的人生最终只变成： “第二个自己。” 参考与环境 将 @图片 1 和 @图片 2 严格作为人物身份锚点。 本轮上传的全部背景与地点参考图共同决定同一套环境 DNA。 正式构图前，无声重组彼此兼容的： 真实地形 建筑语言 材质年代 植被 水体 天气 山雾 倒影 主光方向 空气纵深 形成一个全新的统一地点。 背景原则 背景始终持续鲜活，但在叙事上绝对中立。 角色设定 角色 ID A｜剑仙师姐 始终是同一个 @图片 1 剑仙师姐： 25–30 岁东亚女性 椭圆白皙面庞 深色杏眼 黑色长发半挽，以白玉簪固定 身材高挑纤细 穿同一套白色刺绣真丝汉服 半透明宽袖 银色腰封 玉佩 白色布靴 持唯一一柄银色长剑 角色 ID B｜小师妹 始终是同一个 @图片 2 小师妹： 20–25 岁东亚女性 圆润灵动的脸 黑发编辫 身形娇小 穿同一套青绿色亚麻汉服 深色腰带 木簪 黑色布鞋 持唯一一柄已经有使用磨损的深色钢剑 其他次要角色 一名年长师父 两名宗门弟子 一名外宗使者 这些角色只作为次要见证者存在。 分段结构 0–5s｜全景或远景 一名年长师父主持正式传位仪式。 他双手递出一柄象征剑首身份的礼仪银剑，沉声说道： “接剑。从今日起，你继她的位。” 同一个小师妹下意识伸手。 手指还没有碰到剑， 同一个白衣剑仙突然出剑，只用一次极干净、克制的剑身碰撞把礼仪银剑拨向侧面，绝不能攻击任何人。 她只说： “她不接。” 小师妹立即转头看她： “为什么？” 5–10s｜中景或牛仔景 保持： 同样两名女子 同样服装 同样长剑 同一柄礼仪剑 完全一致的地理空间 师父明显不悦： “你不认她？” 师姐真正看向小师妹，回答： “正因为认。” 完整停顿半拍，再落下一句： “我的位置，只够站一个我。” 浅景深后方，同一个外宗使者忍不住轻笑： “那她算什么？” 师姐甚至没有转头回应这个问题，只继续看着小师妹： “问你自己。” 这一刻不要煽情音乐强推情绪，只保留自然空间声与低而克制的配乐底色。 背景中的以下元素继续自然运动，却完全不介入剧情： 风 水体 山雾 衣袖 发丝 倒影 远处人物 10–15s｜特写或极近特写 同一个小师妹先低头看一眼被拨开的礼仪银剑，又看向自己手里那柄陪伴她多年的旧深色钢剑。 她不再问自己能不能继位，而是换了一个问题，低声问： “那我站哪儿？” 同一个师姐没有替她决定身份，只回答： “别站我后面。” 完整停顿半拍。 小师妹真正听懂之后，从原先落后师姐半步的位置走出来，第一次主动与师姐并肩站立，侧头问： “这儿？” 师姐始终看着前方，没有赞美，也没有安慰，只再说三个字： “再往前。” 极近特写跟随小师妹的眼神变化： 她短暂愣住，随后真正向前走出完整一步，第一次站到师姐前方。 师姐没有伸手拉她，也没有叫她回来。 浅景深后方： 同一个年长师父彻底沉默 那个刚才还在轻笑的外宗使者也慢慢收起笑容 最终画面明确停在： “小师妹拿着自己的旧剑站在最前方” 被拨开的传承银剑仍留在后方，没有任何人再去捡它。 这意味着： 不是小师妹继承了师姐的位置， 而是师姐第一次把前面的位置，真正让给她自己去走。 戏剧核心 整段真正完成的不是“拒绝传位”，而是： 拒绝把小师妹定义成“下一个师姐” 拒绝把认可等同于复制 让她不再作为谁的延续存在 让她第一次站到属于自己的位置上 表演原则 剑仙师姐 不能煽情 不能说教 不能像在做牺牲式成全 她的态度必须稳定、克制、坚定 她不是否认小师妹，而是拒绝小师妹被自己的名号吞没 小师妹 前半段必须处于“顺着大家期待去接位”的自然状态 中段听不懂，但开始动摇 后段真正听懂“别站我后面”的含义 情绪不能爆发式外放 必须主要靠眼神变化和站位变化完成成长 年长师父 起初代表制度与传统秩序 最后沉默本身就是态度变化 不需要认错，也不需要解释 外宗使者 起初带一点旁观者的轻慢 最后收起笑容，说明他也意识到这不是简单的拒绝，而是更高层级的认可 硬性要求 严格总时长 15 秒 16:9 横屏 严格 三个连续清晰镜头 原生同步普通话对白 精准口型 精准视线关系 人物身份全程稳定 发型全程稳定 服装全程稳定 两人原有长剑全程稳定 礼仪银剑全程稳定 配角位置全程稳定 地理空间全程稳定 人物动作数量严格克制 以下三个动作必须清楚可读： 剑身拨开 回头 迈步 微表情必须真实克制 真丝衣料、金属长剑和头发物理效果自然 前景、中景、远景保持真实视差和同步空间环境声 不生成字幕 Seedance 2.0 Mini 执行重点 针对 Seedance 2.0 Mini，重点强化： 人物参考一致性 多人物视觉主次 少而精准的动作节点 稳定摄影机连续性 光影连续性 核心道具连续性 对白、金属轻碰声、脚步声、衣料声和环境声的精准音画同步 Negative blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Create an ultra-realistic cinematic Japanese lifestyle vlog featuring a young Japanese woman enjoying a peaceful rainy day in a quiet Japanese neighborhood. A young woman with black hair tied in a neat ponytail, wearing a white and navy striped oversized T-shirt, beige shorts, and white sneakers, stands under a traditional covered bus stop during light rain. She looks outside, gently extends her hand to feel the raindrops, then turns around and runs playfully along a quiet residential street. Show cinematic transitions of her running through the wet neighborhood, passing traditional Japanese houses, green trees, and a peaceful park. She eventually reaches a wooden shelter in the park, adjusts her ponytail, stretches her arms, and smiles naturally toward the camera. Visual Style: Photorealistic Japanese slice-of-life cinematography, soft overcast daylight, realistic rain reflections, natural human movements, beautiful greenery, peaceful atmosphere, authentic Japanese residential environment. Camera Direction: Start with a cinematic side-profile close-up, transition into a medium shot of her touching raindrops, followed by a smooth rear tracking shot while running. Finish with emotional close-ups and a warm natural smile. Technical: 4K, 9:16 vertical, 24fps, realistic facial expressions, consistent character identity, smooth camera movement, natural physics, detailed environment, cinematic color grading. Important: Maintain the same woman's face, hairstyle, outfit, and body proportions throughout every scene. No facial distortion, no outfit changes, no unnatural movements, no text or watermark.

EMBER FRACTURE — AWAKENING Image SO-YEON | 30s | 16:9 | one continuous generation. LIVE-ACTION ONLY: Ultra-photorealistic AAA supernatural martial arts. <<<image_1>>> locks SO-YEON's exact identity; same single woman throughout. Small 160cm build, messy black hair, black hoodie/pants/Converse. Real skin, pores, hair, eyes and biomechanics. Never CGI/digital double. ALLEY: Wet narrow convenience-store alley at night, red/pink/teal neon, puddles, crates, dumpster, vending machine, steam. 5 unarmed male delinquents attack aggressively, never taking turns. AUDIO: Korean dialogue, diegetic impacts/traffic/ambience only. No BGM/subtitles. AWAKENED COMBAT: Her body takes over automatically; unarmed Taekwondo × Karate × Pencak Silat, extremely fast, fluid chained movement with no reset poses. VFX LOCK: Acceleration = physical movement + subtle heat-shimmer/refractive distortion only. No fire, flames, embers, orange particles, beams, plasma or teleportation. Every strong physical impact creates a brief glass-like spiderweb fracture in the air, splitting neon light, then silently disappearing; realistic steam/dust/debris from impact. IMPACT → FRACTURE WEB → NEON REFRACTION → DISSIPATION. 00–03: So-Yeon cowers against wall. Leader smacks her head. She slowly glares through bangs. {어쭈? 이 년 봐라? 많이 컸다?} 03–06: Fear returns; she flinches: {아…! 미안…}. Leader swings again. 06–09: 0.3s slow-mo: automatic head-slip → Silat parry → pivot → body punch. Fracture flash. Leader crashes into crates. 09–12: She stares at trembling hand in disbelief. {저 년이?!} Four rush simultaneously. 12–17: Heat-shimmer dash through two: parry → redirect → elbow → sweep → side kick. Impact fracture + steam. Continue instantly. 17–22: Two attack together: diagonal dash → duck → shoulder redirect → roundhouse. Wide fracture-web splits pink/teal neon. 22–27: Final attacker from behind. Maximum physical dash; camera lags/whip-pans. Evade → parry → jab → body punch → low kick → spinning back kick. 0.25s slow-mo; dense fracture-web across wall. 27–30: Largest fracture lattice spreads across alley, neon reflections split, debris/crates fly, enemy slides away. Fracture hits lens → brief refracted distortion. So-Yeon studies her hands, then calmly walks through steam, half frightened/half amazed, hair falling over eyes. Never looks back. CUT. CAMERA: Close, kinetic handheld pursuit; tracking, whip-pans, low angles, OTS, facial impacts, rapid focus. Camera reacts slightly late to acceleration. Impact shake only on physical contact. Readable action > chaos. HARD LOCK: Real human + real environment + VFX in same frame. No duplicate So-Yeon. No teleportation. Every VFX effect must originate from visible physical contact.

The robot kiss the man on the cheek and says “I love you dad” The man kisses the robot on the forehead and says “I love you too Rocket” The horses and dogs circle around them playfully.

Went out for milk, came back barefoot 😭 GENERATED With Seedance 2.5 Prompt: 👇 Create a 30-second ultra-realistic Korean summer-morning vlog set in South Korea in the early 2000s, filmed casually by a friend on an authentic consumer DV camcorder. It must feel like genuine home-video footage, not a modern video with a retro filter. CHARACTER: The same young Korean woman in her early 20s throughout. Natural appearance, black wavy hair in a loose messy side ponytail, fitted pastel-blue short top, loose white pajama pants, simple silver necklace, casual flat sandals. Realistic skin texture, minimal makeup, natural expressions and movement. LOCATION: A peaceful Korean residential neighborhood on a warm early-summer morning. Narrow concrete lane, small old houses, weathered concrete walls, potted plants, bicycles, utility poles, overhead wires, laundry hanging outside, and a small neighborhood convenience store. CRITICAL SANDAL RULE (highest priority): From 0s until 17s, BOTH sandals are worn on her feet, properly on both feet, and she holds NO footwear in either hand at any point. Her only hand-held item before 17s is the cloth shopping bag (and later the milk inside it). The sandals come off her feet ONLY at the end of the FINAL ATTEMPT scene (around 21–23s). Before that moment, no sandal may appear in her hand, under her arm, or anywhere except on her feet. EXACT ORDER, 6 SCENES: 0–4s, LEAVING HOME: She steps out of her house wearing both sandals on her feet, holding only a small cloth shopping bag. She locks the door and starts walking down the narrow lane. Both feet in sandals, hands free of footwear. 4–8s, SCHOOL CHILDREN: A few school children with backpacks walk past her. She smiles, waves and says "Good morning!" The children wave back happily and continue ahead toward school. She is still wearing both sandals normally. 8–12s, STORE: She enters the small convenience store (door chime), buys one carton of milk, puts it carefully in her bag and walks back out. Both sandals still on her feet, nothing in her hands except the bag. 12–17s, SANDAL TROUBLE: Walking home through the same lane, she suddenly stops and looks down. The strap of her right sandal has come loose, but the sandal is still on her foot. She pushes the strap back with her fingers and it slips out again. She crouches and tries another way to fix it while the sandal stays on her foot, but it won't stay. 17–23s, FINAL ATTEMPT: The friend zooms in awkwardly. She laughs, makes one last attempt, and the strap pops loose again. Only now, she gives up, takes off both sandals and holds them together in one hand, with the milk bag in the other hand. This is the FIRST moment any sandal is in her hand. 23–30s, BAREFOOT WALK: She walks barefoot down the sunny lane, sandals in one hand, milk bag in the other. The same school children, now farther ahead, notice her sandals and smile, and she laughs and waves. She turns to the camera and says, "I only went out for milk." She keeps w

Create a 30-second ultra-realistic fictional home-video featuring an adult Korean man in his late 20s spending a cheerful afternoon in an older Seoul residential neighborhood. CHARACTER: A fictional adult Korean man in his late 20s with medium-to-long dark hair tied in a casual low ponytail, natural masculine facial features, realistic skin texture and a friendly expressive personality. Keep his appearance consistent throughout the entire video. OUTFIT: He wears a bold, fashionable summer outfit consisting of a vivid red fitted T-shirt, high-waisted relaxed-fit white denim shorts, clean casual sneakers, a simple bracelet, small understated earrings and a small shoulder bag. The outfit is youthful, colorful and stylish, appropriate for a warm summer day. SCENE 1 — LEAVING HOME He steps out of an older Seoul apartment building carrying a small reusable shopping bag. He closes the gate behind him, notices the camera and gives a spontaneous smile before walking down the quiet residential lane. SCENE 2 — LOCAL BAKERY He enters a tiny neighborhood bakery, looks through the pastry display and chooses a small baked treat. He pays the shopkeeper with coins, thanks them and walks back outside. SCENE 3 — FRIENDLY ENCOUNTER While walking through the narrow lane, he suddenly sees his adult male friend approaching from the opposite direction. They smile, greet each other warmly and share a quick friendly hug. They chat and laugh for a moment before waving goodbye and continuing in opposite directions. SCENE 4 — FRUIT STAND He stops at a small roadside fruit stall and chooses a peach. He pays the vendor, places it inside his shopping bag and continues walking. SCENE 5 — EVERYDAY NEIGHBORHOOD MOMENT He walks beneath trees while eating his pastry. A bicycle passes nearby, and he naturally steps aside. He looks around at the quiet houses and smiles as the camera follows him from a short distance. SCENE 6 — ENDING He reaches the end of the lane, turns toward the camera and gives a cheerful wave. He smiles naturally and says, “Bye bye!” He then turns around and walks away down the residential street while carrying his bag and peach. The camera stays behind him until he disappears around the corner. CAMERA STYLE: Authentic early-2000s consumer MiniDV home-video footage. Handheld camera shake, imperfect framing, autofocus hunting, automatic exposure fluctuations, soft digital detail, mild digital noise, slight compression artifacts, realistic motion blur and occasional awkward zooms. It should feel like a genuine recording made by a friend or family member, not a professional production. AUDIO: Only natural neighborhood sounds: footsteps, bicycles, distant traffic, bakery activity, casual conversations, birds, children playing and light wind. No music, no narration, no subtitles, no text overlays, no beauty filter, no sexualized

生成一条10秒真实旅行Vlog风格短视频。主角始终是同一位年轻亚洲女性，人物五官、发型、服装、身材比例全程保持一致，不换脸、不换衣服。 整个视频分为3个独立场景，北京、上海、广州。城市切换使用“响指后直接硬切”的方式完成，不做背景融合，不做空间扭曲，不做建筑叠化。 0-3秒，北京。 女生站在北京具有代表性的城市地标附近，神态自然放松，双手空闲。她看向镜头，抬起右手打一个响指。响指完成后，画面立刻硬切到上海。 3-6秒，上海。 女生已经站在上海外滩或陆家嘴附近，右手拿着一杯咖啡，自然向前走两步，然后喝一口咖啡。 喝完后，她走到旁边可以放置物品的栏杆平台或小桌边，明确地把右手中的咖啡杯放下。咖啡杯必须真实接触平台，手指完全松开，右手彻底离开咖啡杯。停顿约半秒，确认右手已经空出来。 然后她再抬起右手打一个响指。响指完成后画面立即硬切到广州。咖啡杯留在上海原位置，不随人物瞬移，不允许咖啡杯凭空消失、悬空、变形或突然换手。 6-10秒，广州。 女生空手出现在广州塔附近。她自然向前走两步，转身看一眼广州塔，然后站到合适位置和广州塔合影，最后轻轻看向镜头微笑结束。 全程保持真实手机旅行Vlog质感，轻微手持感，动作自然简单，人物重心和肢体运动符合真实物理规律。 特别强调： 上海段右手拿咖啡 → 喝一口 → 把咖啡杯放到固定平台 → 完全松手 → 右手空出来 → 再打响指。 不允许跳过“放下咖啡”这个动作，不允许咖啡杯直接消失。 避免：人物换脸、服装变化、身体比例变化、人物复制、多余手臂、手指畸形、咖啡杯消失、咖啡杯变形、杯子悬空、杯子换手、人物拿着咖啡同时打响指、建筑融合、北京上海广州地标同时出现、城市背景残影、过度复杂运镜。

Character consistency: Same young adult female traveler throughout, same face, hairstyle, body proportions and outfit, realistic skin, natural expressions, cinematic photorealistic travel-vlog style, smooth camera movement, realistic lighting. No face changes, no outfit changes. 0–5 sec — Arrival 🇬🇧 Young female traveler arrives in London, walking out of Heathrow Airport with a small suitcase, excited expression, cinematic establishing shot of London atmosphere, natural handheld vlog camera movement. 5–10 sec — Big Ben & Westminster She walks near Big Ben and Westminster, looks at the landmark and smiles toward the camera, quick selfie-style vlog shot followed by a wide cinematic view of Big Ben and the River Thames. 10–15 sec — Tower Bridge She explores Tower Bridge, walking across the bridge while filming herself, London skyline in the background, natural tourist atmosphere, smooth tracking shot. 15–20 sec — London Street She walks through a beautiful London street with classic red buses, black cabs and historic buildings, briefly stops at a cozy café, takes a coffee and continues exploring. 20–25 sec — London Eye She stands beside the London Eye during golden hour, looks toward the camera with a happy travel-vlog expression, camera slowly circles around her with the London skyline behind. 25–30 sec — Final London Shot She walks along the River Thames at sunset, turns toward the camera and smiles, cinematic aerial pull-back revealing London skyline, warm golden-hour lighting, beautiful travel-vlog ending. Overall: photorealistic, cinematic 4K, natural movement, realistic London environment, smooth transitions between locations, consistent character, consistent clothes, consistent face, no text, no watermark.

Ultra-realistic cinematic action scene inside a high-school basketball gym, a fierce young woman in a stylish school-uniform-inspired outfit unleashes powerful glowing red and purple supernatural energy from her hands, intense confrontation with another girl, dramatic energy trails and particles, dynamic movement, wooden basketball court, bleachers in the background, cinematic lighting, realistic facial details, dramatic atmosphere, motion blur, volumetric light, shallow depth of field, high contrast, photorealistic VFX, 8K detail, vertical 9:16 composition, epic supernatural action movie aesthetic.

A tiny hand-drawn 2D animated explorer discovers a giant abandoned clockwork workshop, turning gears, springs, buttons, and mechanical objects into a thrilling miniature obstacle course. Style: Mixed-reality hybrid animation combining expressive hand-drawn 2D character art with a realistic mechanical workshop environment. Playful stop-motion physics, smooth hand-drawn motion, cinematic lighting, realistic textures, and detailed mechanical sound effects with energetic background music. Camera & Framing: Extreme macro close-ups, low-angle tracking shots, dynamic overhead views, shallow depth of field, tilt-shift miniature effects, and fast cinematic camera movements following the tiny explorer. Audio & Scene Breakdown [00:00] - [00:03] Visual: A tiny explorer wearing a blue jacket, brown boots, and a small red backpack stands beside a massive brass gear as it slowly begins rotating. [00:04] - [00:07] Visual: She jumps onto the moving gear teeth, runs across them, and leaps onto a giant metal spring that launches her onto a wooden workbench. [00:08] - [00:12] Visual: A huge mechanical lever suddenly moves beneath her, sending her sliding across a polished metal surface before she grabs a dangling copper wire. [00:13] - [00:17] Visual: She swings across the workshop and lands inside an enormous open pocket watch, running between its moving gears as sparks glow in the background. [00:18] - [00:22] Visual: A giant wind-up key begins turning, creating a powerful gust that pushes her across the table while loose screws and metal pieces roll around her. [00:23] - [00:27] Visual: She discovers a tiny glowing blue crystal hidden inside a mechanical box and carefully reaches toward it as the entire workshop begins coming alive. [00:28] - [00:30] Visual: She touches the crystal, causing hundreds of gears to move simultaneously as the camera rapidly pulls backward to reveal the entire workshop operating like one enormous machine. Maintain consistent character design, proportions, environment scale, lighting, textures, motion physics, and visual style throughout the entire video. Use original characters and environments only. No logos, text, watermarks, branded elements, or recognizable copyrighted characters.

日本の地域イベント。着ぐるみの頭を外す瞬間から始まる、さくらの短い休憩。乱れた前髪、汗を拭く手、水を飲んで抜ける肩の力。スタッフと目を合わせてうなずき、再び頭をかぶって会場へ。 後半は子どもたちとの交流と記念撮影。嬉しくて近づく子どもたち、並ぶまでの小さな慌ただしさ、スマートフォンを構える保護者。着ぐるみの中のさくらは、相手の高さへ手を下げ、その動きを待つ。 撮影は付き添う友人の横向きスマートフォン。軽い手ブレ、追従の遅れ、構図の迷い。演技を強調せず、行動と環境音で見せる。セリフ・字幕・BGMなし。 【着ぐるみの設計指示】 着ぐるみはオリジナルの犬型キャラクターとして設計する。既存のアニメ・ゲーム・商品・企業・自治体のキャラクターや、着ぐるみ制作会社の既存デザインを参照・模倣しない。特定キャラクターの特徴的な輪郭、耳、目・鼻・口の配置、配色、模様、衣装、装飾の組み合わせを再現しない。既存キャラの色替えや部分変更ではなく、独自の造形として構成する。

Create a realistic cinematic superhero speed sequence in a busy downtown city street during autumn, with natural daylight, pedestrians, cars, crosswalks and detailed buildings. Scene 1 — Wide street-level shot: pedestrians cross a busy intersection while cars wait in the background. Camera tracks smoothly from left to right. Scene 2 — A female superhero in a sleek fitted red superhero suit suddenly appears and accelerates across the crosswalk at extreme speed, powerful running posture, flowing hair. Scene 3 — Side-tracking close shot: she races past outdoor café tables and pedestrians, surrounded by intense glowing red energy trails and realistic motion blur. Scene 4 — Low-angle tracking shot: she rapidly approaches a small white dog in the crosswalk, crouches down while still moving at super speed and safely grabs the dog. Scene 5 — Close dynamic shot: she carries the dog securely while sprinting forward, red energy streaks wrapping around her body, strong cinematic motion blur. Scene 6 — Wide establishing shot: she races across the entire intersection at incredible speed, leaving long red light trails behind her as pedestrians react naturally. Scene 7 — Fast lateral camera pan: she blasts past people sitting on a city bench reading newspapers, red energy trails sweeping through the frame. Scene 8 — Final wide-to-medium tracking shot: she continues running rapidly down the street and toward the camera, then passes close to the camera with powerful speed, realistic cinematic lighting and motion blur. Photorealistic, cinematic superhero VFX, realistic human movement, natural city environment, dynamic camera tracking, shallow depth of field, realistic red energy trails, high detail, smooth motion, dramatic speed-ramp feeling, no text, no logos, no watermark.

30 sec | 16:9 | One continuous generation | English dialogue | No BGM | No subtitles STYLE: Ultra-photorealistic live-action premium smartphone commercial with the cinematic visual language of a coming-of-age movie. Real actress, real environment, natural practical lighting, subtle 35mm film grain, realistic skin texture, physically accurate reflections, natural handheld imperfections. The first half must feel like a movie scene, while the product is gradually revealed as the reason the moment exists. CHARACTER LOCK: YOUNG WOMAN from the provided reference image. Same actress throughout. Long messy wavy dark-brown hair, natural skin texture, grey fitted cropped T-shirt, black high-waisted jeans. Preserve her exact facial appearance, hairstyle, clothing, body proportions and styling from the reference image. Natural micro-expressions, subtle acting, realistic movement. PRODUCT LOCK: VELORA V1, fictional premium smartphone based exactly on the provided phone reference image. Deep burgundy metallic body, ultra-thin flat frame, minimal black dual-camera module, subtle silver "V" logo centered on the back, premium glass finish. Keep the exact same phone design, proportions, color, camera placement and logo throughout the entire video. No real-world smartphone branding. LOCATION: Outdoor rooftop terrace at blue hour. Deep navy evening sky with a faint warm pink horizon, distant trees and soft city lights. Weathered concrete ledge. Gentle natural wind. Quiet cinematic atmosphere. SOUND: Natural location sound only. Evening wind, distant traffic, footsteps, fabric movement, subtle breathing, realistic phone camera sounds and interface clicks. No music. STORY: The commercial begins as if it is a scene from a real movie. The audience does not immediately realize they are watching a smartphone advertisement. 00:00–05:00 — SETTING THE CAMERA Extreme close-up of a hand carrying the burgundy VELORA V1. The hand places the phone carefully on a concrete ledge. Close-up of the phone's burgundy metallic back catching the blue-hour light. The girl reaches toward the phone. She taps the screen. The front camera opens. The phone screen shows her live preview. She adjusts the phone angle slightly until the composition matches the provided girl reference image. She steps backward. A small realistic recording indicator appears: "REC 00:00" Camera remains fixed as if the phone itself is recording. 05:00–11:00 — THE REFERENCE PHOTO COMES ALIVE The recorded footage now becomes the main visual. Recreate the exact composition and appearance of the provided girl reference image: Low-angle perspective. Deep blue evening sky. Long messy wavy hair. Grey cropped T-shirt. Black jeans. Natural direct-camera expression. She stands still for a moment. A gentle gust of wind moves her hair naturally across her face. She looks directly into the front camera. She gives a tiny genuine smile. She quietly says: "Ok

CAMERA/LOOK: DV 16mm tape camcorder POV, handheld/propped shots. Shaky framing, imperfect focus, clumsy zooms, occasional face cut-offs. Soft blurry tape quality, faint noise, bloomed gym lights, flickering exposure, muted contrast, realistic skin tones. Camcorder never visible. STYLE: Playful, self-deprecating gym vlog. Genuine strain, humor, quick energetic cuts, lighthearted rather than exhausted. CHARACTER: CHASE, Korean idol in her 20s. Long black high ponytail, glowing slightly sweaty skin, expressive eyes, slim athletic build. Modest long-sleeve athletic top, joggers/leggings, socks, no jewelry. SETTING: Evening gym mat area, nearby mirrors, water bottle on floor, soft overhead lighting, equipment in background. 15s / 6 CUTS: 1. (~2.5s) Propped medium shot. CHASE lies on mat, propped on elbows, sighing dramatically. "Okay, core day — my least favorite day." 2. (~2.5s) Plank, slight arm shaking, strained expression. "Why does this get harder every single time—" 3. (~2.5s) Crunches, breathing hard and complaining between reps. "Nobody warns you how much this actually burns." 4. (~2s) Macro close-up, shallow DOF. Hands grip mat during leg raises, abs visibly working. No dialogue, gym ambience. 5. (~2.5s) Handheld/propped shot. Finishes leg raises, flops onto mat laughing. "Okay— that's it, I'm done—" 6. (~3s) Arm's-length selfie while lying on mat, tired grin. "Core day never gets easier — see you guys tomorrow, hopefully."