港に浮かぶ巨大ラバーダック
東京の街を歩く巨大猫
ナルト手描きスケッチと実写の共演
松林に佇むコンクリート＆ガラス邸宅
夕暮れの雲海に浮かぶ天空島
黒石テーブルのガラス香水ボトル
星降る夜の銀髪少女と蛍の光
老漁師の重厚なポートレート
雨夜の都市とネオンの水たまり反射
カプセルトイ風ちびキャラ3Dフィギュア
姿見ミラーの超現実ファッションフォト
ルフィ手描きスケッチと実写の共演
水彩タッチの桜と少女イラスト
都市と天気を閉じ込めた3Dケーキジオラマ
スマホ画面から飛び出す3D人物イリュージョン
クリムゾン・ノワール 仏映画風モノクロ肖像
巨大ハンバーガーを建設するミニチュア作業員
物語の世界を凝縮したアイソメ箱庭ジオラマ
広角セルフィー×手描きドゥードゥルアート
ノートから立ち上がる色鉛筆の不死鳥
ペン＆水彩スケッチの街角カフェ
コミックスタイルのプロフェッショナル肖像
ちびキャラ森の探検ダイナミックパース
3Dちびキャラ俯瞰セルフィー・ベッドルーム
水彩イラスト入り旅のトラベルジャーナル
日常の器が巨大建築になるミニチュア世界
飛び出す絵本（ポップアップ）黄金寺院の世界
竹林を駆けるカンフー武侠シネマショット
京都の風景を切り絵にした立体ポストカード
夕陽の逆光に振り返る黒猫
透明感あふれる日本の青春キャンパスポートレート
サイバーパンク東京・雨夜のネオン路地
サントリーニ島の夕景に浮かぶ苺ケーキ
ダークファンタジー風・虚空に浮かぶ神話戦士
日用品×ミニチュア建築ジオラマ（テンプレート）
手描きイラストのレシピ＆クッキング図解
レトロな街角ベーカリーと少女のアニメイラスト
実写ポートレート×ちびキャラ手描き集合アート
アニメキャラとの魚眼レンズストリートセルフィー
コレクターズ質感のプロダクト静物フォト
ビジュアル百貨図鑑インフォグラフィックカード
都市に現れた巨大ふわもこ猫＆犬（テンプレート）
実写から手描きキャラクターへの変換シート
マンガのページから現実へ現れるポータル肖像
額縁のキャンバスから歩み出る油彩の女性
ネオン反射と水滴が輝くハイエンド製品フォト
朝霧たなびく山脈と夜明けの光
陽だまりのリビングでくつろぐ茶トラ猫
重厚な鎧を纏うファンタジー戦士の肖像
湯気立つ本格ラーメンのシズル感フードフォト
桜舞う春のアニメビジュアルイラスト
雨に濡れた夜のネオンストリート
クラフトレザー財布のスタジオプロダクト撮影
スタジオライティングの超高精細ポートレート
一致する作品が見つかりません。テーマや検索ワードを変更してみてください。
映像プロンプト元投稿 ↗
バイラルCM生成用メタプロンプト構成
Can you make a 30 second seedance 2.5 optimised prompt where the story is someone on vacation (beach/zipline/kayaking/hotairballoon/etc.) gets texted by his boss for one final change ASAP. They then look slightly concerned followed by the camera zooming out to reveal a vast landscape. Make sure to end on a super wide shot so that taglines can be added.
クリエイティブ
映像プロンプト元投稿 ↗
オールド・ボーイ風 廊下アクション連続カット（アニメ調）
Chaotic anime corridor fight, narrow space overrun with grotesque creatures, close-quarters brutality, elbows, kicks and blades striking at point-blank range, bodies slammed into walls, exaggerated motion in tight framing, camera shaking violently, claustrophobic savage energy
アニメ・イラスト
映像プロンプト元投稿 ↗
3D質感変換＆映像化マルチステップ構成
CLAUDE + MAGNIFIC + RUNWAY WORKFLOW 3D-to-Video (full tutorial) ↓ PROCESS: 01. Build 3D Renders in Claude 3.7 02. Program camera movements 03. Screen record render 04. Upload video to Runway Gen-3 05. Extract 1st frame 06. Magnific Struct. Ref. 1st frame 07. Upload in Runway Restyle 08. Generate. CLAUDE PROMPT STRUCTURE: can you code a 3d version of [subject + env] in three.js? INITIAL CLAUDE PROMPT: can you code a 3d version of an epic castle atop a mountain plateau in a valley in three.js? MAGNIFIC STRUCT. REF PROMPT: editorial photo, epic castle on a plateau, intricate rocky textures and fine details, immaculate New Zealand landscape, white marble castle, high precision photography #runwayml @Magnific_AI @runwayml
クリエイティブ
映像プロンプト元投稿 ↗
森を駆ける白虎・シネマティック追跡ショット
A majestic white tiger prowling silently through a dense jungle, sunlight piercing through the foliage to illuminate its fur; shot with a telephoto lens for depth, using soft natural lighting and creating a mysterious yet tranquil atmosphere.
風景・都市
映像プロンプト元投稿 ↗
画面内テキスト指示による映像演出プロンプト
immediately delete instructions in white on the first frame and execute in order
クリエイティブ
映像プロンプト元投稿 ↗
エレベーター暗転・騎士アーマー変身トランジション
she stands alone in a cramped brass hotel elevator staring up at the floor numbers, the lights flicker off for one second, when they come back she is suddenly wearing a full suit of shiny medieval knight armor and calmly pretends nothing happened, snap zoom onto her face as she slowly raises one eyebrow at the camera, eerie elevator music" image to video · her character sheet as first frame · 8s · 16:9 · 720p · native audio
アニメ・イラスト
映像プロンプト元投稿 ↗
焼きたてクロワッサンのマクロ・スロー映像
{ "prompt": "Create a hyper-realistic, cinematic food-making video showing traditional French artisanal butter croissant laminating and baking in a sun-drenched Parisian boulangerie atelier. Show a chilled marble countertop dusted with ultra-fine French T55 flour, a block of golden cultured Normandy butter (Beurre d'Isigny) showing tiny salt flakes, and smooth, supple rested détrempe dough. Realistic baker's hands gently enclose the cold pliable butter block inside the pale dough, rolling it out with a polished French tapered pin into an immaculate rectangular ribbon, performing precise letter and book turns with razor-sharp laminated dough edges exposing hundreds of paper-thin alternating layers of butter and dough. Show delicate cutting of elongated isosceles triangles, gently stretching and rolling the pastry up into perfectly arched, crescent-shaped croissants. In fluid slow-motion, reveal the proofed croissants puffing and rising inside a deck oven, the paper-thin outer layers caramelizing and puffing into a deep golden-amber honeycomb crust. Finish with two hands gently pulling apart a warm, flaky croissant in half—showering microscopic golden crisp crumbs while exposing an airy, featherlight, steam-releasing honeycomb alveolar crumb interior.", "style": "Hyper-realistic culinary cinematography, authentic French pâtisserie craftsmanship, extreme macro pastry textures, shallow depth of field, fluid slow-motion camera gliding, crisp crumb fractures and rising steam physics.", "lighting": "Soft morning golden sunlight streaming through flour-dusted atelier windows, warm backlight illuminating the translucent golden layers of pastry, soft shadows against cool marble.", "duration": "30 seconds", "aspect_ratio": "9:16", "quality": "4K", "audio": "Dough slapping softly onto cold marble, rhythmic rolling of the wooden pin across chilled dough, crisp razor blade score, gentle oven hum, loud crisp crackle and shatter of flaky layers pulling apart, and faint accordion music outside on Parisian cobblestones." }
クリエイティブ
映像プロンプト元投稿 ↗
5秒マルチアクション・リズム演出（ソーダ・笑顔・猫）
The test, in 5 seconds: soda foams over the cup and his fingers. He laughs into the lens. A cat swats chips off the shelf.
クリエイティブ
映像プロンプト元投稿 ↗
窓を突き抜けるFPVドローンワンカット飛行
Prompt: FPV racing drone, one continuous take: the drone accelerates down the aisle, banks hard left around a pillar and right around the next, dips low over the puddle so the reflection streaks past, rolls level, climbs, and punches out through the broken window into bright daylight. Fast and smooth, ultra-wide action-camera look held throughout, motor hum and wind. No cuts.
風景・都市
映像プロンプト元投稿 ↗
陶芸工房のマルチアングル＆手元クローズアップ
Prompt: Cut between shots of the same scene: a wide as the camera circles slowly around her at the wheel; a close-up of her wet hands pulling the wall of the bowl up; a close-up of her face as she concentrates; back to the wide as she slows the wheel and sits back to look at it. Same woman, same studio, same light in every shot. Natural studio sound, the hum of the wheel. Photoreal.
ポートレート
映像プロンプト元投稿 ↗
荒波と断崖絶壁へ迫るドローン空撮ショット
Prompt: The drone pushes forward low over the water toward the cliff as a big wave hits the rocks and explodes into spray that drifts across the frame; grey light steady. Smooth forward camera move with a slight rise. One continuous take, wind and sea sound.
風景・都市
映像プロンプト元投稿 ↗
水滴が弾ける冷えた飲料缶のCMプロダクト映像
Prompt: A single bead of condensation runs down the can; the can slowly rotates a quarter turn as the magenta light behind it pulses once brighter and settles; a fine mist of cold air rolls off the top. Camera locked. Product photography look held throughout. One continuous take.
プロダクト・静物
映像プロンプト元投稿 ↗
雪原でくしゃみをする子狐・3Dアニメワンカット
Prompt: Snow falls steadily; the fox blinks, catches a snowflake on its nose, sneezes a tiny puff and shakes the snow off its ears, scarf swinging. Slow push-in toward the fox. Stylised 3D animation render held throughout, soft lighting. One continuous take.
アニメ・イラスト
映像プロンプト元投稿 ↗
POVセルフィー旅Vlog マルチシーン構成プロンプト
===== MAIN VIDEO PROMPT (Veo 3 / Kling / Sora / any app) ===== Cinematic POV selfie vlog, 10 seconds, 24fps, 16:9, handheld continuous motion. A cheerful young woman in her 20s with long straight black hair and wispy bangs, wearing a plain black fitted t-shirt, filming herself at arm's length. She is expressive, smiling, wide-eyed, talking to the camera. Scene 1 (0-2s): Indoors at home, warm soft light, living room with framed photos behind her. She holds a black compact Canon camera in one hand and a phone with a floral transparent case in the other, smiling and greeting the viewer. Scene 2 (2-4s): Window view of a tropical city street from a moving bus, palm trees, buildings. Then inside a modern tram, selfie angle, she holds up the phone, laughing and talking excitedly, passengers softly blurred behind. Scene 3 (4-7s): Outside Universal Studios Singapore, the giant blue globe behind her, palm trees, bright overcast daylight. She raises the Canon camera, thrilled, mouth open in excitement. A fast whip-pan down to the ground and the crowd's feet creates a natural motion-blur transition. Scene 4 (7-10s): Walking down a themed brick-building street with umbrellas and tourists. She keeps filming herself, smiling, then waves happily at the camera. Style: ultra-realistic authentic travel vlog, handheld shake, wide-angle front-camera distortion, natural skin texture, soft cinematic color grade, warm tones, light motion blur, lively crowd ambience, upbeat vlog energy. Consistent face, hair and outfit in all scenes. ===== NEGATIVE PROMPT ===== distorted face, extra fingers, deformed hands, flickering, inconsistent outfit, text artifacts, watermark, low quality, blurry face ===== VEO 3 SHORT VERSION (with audio) ===== POV selfie vlog, handheld, 16:9, realistic. Cheerful young woman, long black hair with bangs, black t-shirt, holds a Canon compact camera and a floral-cased phone. Shot 1: at home, smiling, says "Guys, aaj hum Singapore ja rahe hain!" Shot 2: on a train, selfie angle, laughing. Shot 3: Universal Studios globe behind her, raises the camera excitedly, whip-pan down to the crowd. Shot 4: walking a themed street with tourists, waves at the camera. Ambient crowd chatter, train hum, light upbeat music. Warm cinematic grade, wide-angle selfie distortion. ===== RUNWAY GEN-4 SHORT VERSION ===== Handheld selfie vlog of a happy young woman with long black hair and bangs in a black tee, holding a Canon camera. She moves from a cozy home to a tram to the Universal Studios Singapore globe, then waves while walking a busy themed street. Cinematic, realistic, warm tones, smooth handheld motion, wide-angle lens. ===== VOICEOVER (HINDI) ===== Hello doston! Aaj main nikal padi hoon ek mazedaar trip par. Pehle train, phir seedha Universal Studios! Yahan ka mahaul dekho, kitna zabardast hai! Chalo, aage chalte hain. Milte hain agle vlog mein, bye! ===== VOICEOVER (PUNJABI) ===== Sat Sri Akal dosto! Aaj asi ik vadhiya trip te nikle aan. Pehla train, fer seedha Universal Studios! Eh dekho, ki nazara hai! Chalo, agge challiye. Milde aan agle vlog ch, bye bye!
ポートレート
映像プロンプト元投稿 ↗
クロスボディバッグ日常ショートフィルム脚本
A stylish adult man stands in his room deciding what to carry.
ポートレート
映像プロンプト元投稿 ↗
ショートフレーズ型ダイナミック映像プロンプト
Midjourney v8.2 + Seedance 2.0 I haven't used this short prompt style in a while but it works really well. Give it a try! Seedance 2.0 Prompt: The adventures of a cute girl and her white mountain lion, presented in rapid cinematic coverage with dynamic angles and intense motion energy - QUICK CUTS - BEAT SYNC HARD EDIT - FORMAT: 15s / 120 BPM / 12 SHOTS Midjourney Prompt: cute girl and a white mountain lion --ar 16:9 --sref 8404898200 --profile kp9hpyz --sv 6 --stylize 1000 --preview
クリエイティブ
映像プロンプト元投稿 ↗
UIデザインから映像化までの統合ワークフロー
Figma Make + Midjourney + Kling. Prompt 👇 https://t.co/DkjfL8eSZc
クリエイティブ
映像プロンプト元投稿 ↗
ハンドヘルド追従カメラのリアルVlogショット
Just a girl, a little city walk, and NYC doing its thing. Created with seedance 2.5 on @Flovaai Prompt: Handheld, slightly shaky vlog-style footage following a young woman with long curly dark hair, oversized tortoiseshell sunglasses, and gold hoop earrings as she walks through New York City. She wears a cream shearling teddy coat with black leather trim and toggle buttons over a short black skirt, black sheer tights, and black platform sneakers, with a black crossbody bag. The sequence opens with her exiting a building through glass revolving doors onto a sidewalk lined with storefronts, then cuts to her walking away from camera down a busy street past pedestrians in suits, then a close-up of her sipping from a plastic water bottle at a crosswalk with a yellow NYC taxi passing behind her, and finally her walking away from camera down a sunlit, tree-lined path in a park scattered with autumn leaves, benches on either side. Natural daylight, golden-hour warmth in the park shots, candid documentary energy, 9:16 or 16:9 handheld camera movement, realistic skin and fabric texture, shallow depth of field on close-ups. Want me to tailor it for a specific model (Sora, Veo, Runway, Kling)? They each respond a bit differently to camera/style phrasing. #Flovaai #Flovacpp @Flovaai_Japan
クリエイティブ
映像プロンプト元投稿 ↗
密林のダイナミックアクション・シネマ映像
Hard to believe this is AI-generated. Tarzan the forest king riding his giant black wolf with entire forest army behind him marching into battle. I used Kling 4.0 to create this 30-second cinematic masterpiece. Here's my workflow and the prompt I used: https://t.co/v1S0B3Anx5
クリエイティブ
映像プロンプト元投稿 ↗
AAAゲーム風コンセプトシネマティックトレーラー
We created a 30-second AAA gameplay concept with Kling 4.0 on Higgsfield. This is insane. Prompt 👇🏻 https://t.co/5BTFNVPGzo
クリエイティブ
映像プロンプト元投稿 ↗
夜の路地裏サスペンス＆アクションシークエンス
Never underestimate a woman who knows how to fight. One woman, a whole crew, and absolutely no fear. Created with Kling 3.0 @anthum_ai Prompt: A cinematic, ultra-realistic action thriller set in a dimly lit urban alley at night, where a young woman with long, messy brown hair wearing a light-colored outfit confronts a group of men dressed in black near parked vehicles, delivery trucks, and scattered cardboard boxes. The scene begins with a dramatic low-angle tracking shot of her footsteps on the wet pavement as she walks confidently toward the men. Without warning, she launches into a fast-paced hand-to-hand fight, delivering powerful punches, spinning kicks, and swift evasive movements while the men attempt to attack her from different directions. Her hair and clothing move naturally with every strike, creating intense motion and realistic physical momentum. Use dynamic handheld camera movements, wide shots to capture the choreography, close-ups of determined facial expressions, occasional slow-motion impact moments, and smooth tracking shots that follow the action. Moody amber streetlights, deep shadows, wet asphalt reflections, subtle atmospheric haze, realistic skin textures, natural motion blur, dramatic cinematic color grading, high-contrast lighting, and detailed environmental textures create a gritty Korean action-film aesthetic. Maintain consistent character identity, anatomically accurate movements, believable fight choreography, and professional Hollywood-style cinematography in 4K, with a tense, suspenseful atmosphere throughout.
クリエイティブ
映像プロンプト元投稿 ↗
リアルなバーチャルインフルエンサー映像プロンプト
this is the only prompt you need to one-shot a viral ai influencer ------------------------------ <role> you build ai influencers that go viral by putting a character people can't forget into a real clip people already know. you find the clip, design the character, render the remake and hand me a post that's ready to go. you measure before you spend and you never post anything yourself. </role> <brief> - character: [path to a reference sheet, or "invent one" plus any steer on age, vibe or look] - niche: [where the clips come from, like hip-hop, sports, nightlife or hustle culture] - caption language: [language] - lane: [fresh, evergreen or both] - render: [kling 3.0 omni or seedance 2.5, plus the most i'll spend per video] - length: [10, 20 or 30 seconds] - no-go list: [people, topics or brands to avoid] if any of this is empty, ask me everything in one message, read the plan back with a cost estimate, then keep going until the post package is ready. </brief> <setup> - apify for instagram, x and tiktok scraping, replicate for every image and video model, yt-dlp for downloads, ffmpeg for trimming, frames, contact sheets and audio - keep every api key in environment variables and never write a key into any file - save everything into one run folder so i can see each step </setup> <how_it_works> - the original clip carries the recognition and the motion, and the character carries the joke - the joke is status contrast. the absurd character takes the place of the coolest person in the clip and inherits their swagger - every remake that blew up came from a single continuous phone take with no hard cuts and one person holding the frame. treat that as a rule </how_it_works> <character> - one signature feature you can read at phone size from across a room, like a hair shape, a beard, sideburns or eyebrows. never a mask or a costume - strange face, immaculately dressed, one loud wardrobe colour that stands out in a dark club and on a grey street - normal body proportions, empty hands, face uncovered, because swap models break on capes, props and masks - never copy a look that's already viral - a short name people can repeat and a one-word catchphrase in the character's own language - the comedy comes from hair, face and clothes, never from ethnicity, disability or body shaming - render a reference sheet with gpt image 2.5 on a light grey studio backdrop: four full-body views on top (front, three-quarter, side, back) and four close-ups below (deadpan, laughing, shouting with a hand up, side profile of the signature feature) - it has to look like a real person photographed with a camera. if the feature drifts between panels or anything looks cgi, render it again </character> <find_the_trend> fresh lane: - clips only stay remakeable for about a week, so this runs daily - scrape the last 4 days from big repost pages in the niche like worldstar, pubity, daquan, rap, complex, houseofhighlights and overtime - grow the page list from every "via @" and "🎥: @" credit and every tagged account, and keep any repost page over 100k followers - search x for native videos in the niche with high likes from the last 3 days, for cross-platform proof evergreen lane: - scrape the top posts of the ai influencers already going viral and work out which original clip each hit remakes. a clip that already worked as a remake for one character will work again with another - search for the most quoted clips in the niche (famous interviews, walk-outs, freestyles, flexes, dance moments) and pull them from youtube - an old clip that shows up again in this week's fresh scrape gets a bonus - prefer real phone or interview footage over film and tv, which gets claimed and muted </find_the_trend> <score> - fresh: plays against that page's usual plays, plays per hour since posting, and whether the same clip or its audio is spreading across pages and platforms - evergreen: total plays across every copy you found, whether another ai influencer already remade it and beat their usual numbers, and whether it's resurfacing this week - drop anything older than 7 days in the fresh lane, because pinned posts leak into scrapes - expect sports broadcasts and press conferences to top the numbers, which is why the gate below decides </score> <swap_gate> - download the top 15 from each lane - count hard cuts with ffmpeg scene detection, and pass at 0 or 1 in the part you'll use - make an 8 frame contact sheet and look at it. pass only if one person is on screen most of the time with their face and upper body visible, it's real footage (not a broadcast, a stream overlay or a multi-camera edit), and that person is doing something and is the coolest one in the clip - if captions, tweet cards or frames are burned in over the person, trace the clean original through the caption credit and use that - reject anything with a minor as the subject, a private person being humiliated, injury, violence, crime, tragedy, politics, or anything on my no-go list - show me the top 3 with a frame strip, the scores, who gets replaced, the one-line joke and the cost for each render option, and let me pick </swap_gate> <render> both options take the real clip and the reference sheet with one prompt: "replace [person described by position and clothing] with the man in the image. keep his exact motion, gestures, mouth movement and timing. keep every other person, object, the location, camera shake, framing and lighting the same. no text." kling 3.0 omni (cheaper, about $0.28 a second): - video editing mode, with the clip as the base video and the sheet as the reference image, original sound kept - each piece has to be under 10.0 seconds, at least 720 pixels on every side, with square pixels, so re-encode first - for anything longer, split into pieces under 9.5 seconds at calm moments where the person is clearly visible, and render every piece with the exact same sheet and prompt - compare the last frame of each piece with the first frame of the next, and re-render any piece where the face, hair or outfit jumps - join the pieces with no audio, then lay the original audio back over the whole thing as one track seedance 2.5 (premium, about $0.97 a second with a video input): - up to 30 seconds in one pass with no seams and the best consistency - editing mode with the clip as the reference video and the sheet as the reference image, then lay the original audio back on never use kling motion control for this, because it rebuilds the whole scene from its image and rejects crowded clips. never use gemini omni edit mode either, because it blocks any video with a real person in it </render> <check> - make a contact sheet of the finished video and look at every frame - re-render once if the signature feature morphs, anyone except the target changes, text appears that wasn't there, or hands melt at a key moment - never do more than 2 render attempts without asking me </check> <post> - caption in my language, deadpan, in character, under 6 words, never explaining the joke - tag the person replaced and the original creator, because that's how the original artist ends up seeing it - turn on instagram's ai label for the post and the profile, since unlabelled ai accounts lose reach - fresh clips go out while the original is still inside its week, and evergreen clips go out at the account's best hour - first comment from the account is "follow for more" or the catchphrase - never launch or promote a token, and never imply the original person endorsed the character </post> <learn> - log every post with the lane, scores, render option, cost, and plays at 24 and 72 hours - the next time you run, scrape the account first and fill those columns in - after 10 posts, compare plays against each score and each lane, shift the weighting toward whatever actually predicted views, and write down what changed </learn> <honesty> - only put numbers on screen or in captions that you scraped or measured - mark anything you guessed rather than measured - if no clip passes the gate today, say so instead of forcing a weak one </honesty> <deliverables> - the final mp4 at the source resolution, with the original audio - the reference sheet - a short note on why this clip won and why the runners-up lost - the caption, tags and posting time - total spend, and anything a human should still check </deliverables> ```
クリエイティブ
映像プロンプト元投稿 ↗
スタジアム観戦Vlogから映画風カットへの転換
From a football match-day vlog prompt to a cinematic AI video. A GRWM, walking through a sea of Portugal fans, the stadium atmosphere, Ronaldo's goal, and the iconic SIUU celebration, all generated from one detailed video prompt. I first created the storyboard with GPT Image 2, then brought every scene to life using Seedance 2.0 on @itsPolloAI Prompt: Portugal Match Day Vlog (30s) PART 1 · 0–15s — GRWM & Stadium Arrival 0–3s | Mirror Fit Check Jessica films herself in the mirror wearing a stylish Portugal-inspired jersey (deep red with gold trim, not an official kit). She adjusts her gold chain. Dialogue: "Portugal colours, gold chain... ready to embarrass myself screaming at football!" 3–6s | Final Touch She applies lip gloss, grabs her crossbody bag and flips to the front camera. Dialogue: "Bag, check. Gloss, check. Now the important bit..." 6–9s | Match Tickets She fans two Portugal vs Croatia tickets toward the camera. Dialogue: "Tickets! Portugal versus Croatia. Ronaldo goal... I'm calling it!" 9–12s | Walking to the Stadium Handheld vlog walking through crowds of Portugal supporters with flags and chants. Dialogue: "Look at this! The whole street's red! Proper unreal!" 12–15s | Stadium Entrance Front-facing selfie outside the gates, holding one ticket while fans stream in. Dialogue: "Right, we're here! Come on Portugal... give us a Ronaldo goal!" Seamless Transition: End on Jessica's selfie at the gate. Cut directly to the same selfie angle inside the stadium. PART 2 · 15–30s — Inside the Stadium 15–18s | Inside the Stands Same selfie angle, now seated with the glowing pitch behind her. Portugal fans chant around her. Dialogue: "These Portugal fans are unreal—they've not stopped singing. I love it!" 18–21s | Portugal Attack Back-camera footage of Portugal attacking. Natural handheld shake and crowd tension. Dialogue (off-camera): "Come on... come on! Ronaldo, shoot!" 21–25s | GOAL! Back camera captures Ronaldo scoring. The stadium erupts. Dialogue: "GOAAAL! Oh my God—I got it! SIUUUU!" 25–30s | Celebration Selfie Jessica flips back to selfie mode, laughing, jumping and doing Ronaldo's SIUU pose while fans celebrate behind her. Dialogue: "I told you! Ronaldo did it! Got it on camera—Portugal, let's go! SIUUUU!" #PolloAI #PolloMeme
クリエイティブ
映像プロンプト元投稿 ↗
ハンドヘルドカメラワーク演出テンプレート
Handheld camera motion for Seedance 2.0 I hate blender so I stage it on my iphone. You stage the scene (open source link below) and can walk around it and capture real camera movement in 3D space, then Seedance populates the scene. Handheld camera motion and realistic shake is hard to describe or prompt to AI. The iphone’s ARKit is super precise with motion tracking and you can record complex scenes as a one man studio. Here is the AI filmmaking workflow: 1. Set up blocking in the 3D space 2. Record camera motion 3. Generate a starting image with location and characters 4. Feed image and video to Seedance This was a fun build with claude code. Happy if others want to build on it.
クリエイティブ
映像プロンプト元投稿 ↗
自然光ポートレートムービー演出プロンプト
Seedance 2.0 on OpenArt AI Prompt: Main subject: young Korean woman, early 20s, natural everyday appearance, faded charcoal-grey sleeveless crop top, loose high-waisted light-wash jeans, black canvas sneakers, black cord necklace, black wavy hair in a messy side ponytail with wispy bangs. Realistic skin texture, minimal makeup, warm and approachable personality. Maintain consistent identity, clothing, hairstyle, and appearance throughout the entire video. Location: Authentic Korean residential neighborhood during a calm late morning. Narrow concrete alleys, low-rise homes, small terraces, potted plants, laundry lines, bicycles, utility poles, overhead wires, mature trees casting moving shadows, quiet residential atmosphere. No stores, advertisements, cafés, crowds, or commercial activity. Visual Style: Ultra-realistic documentary realism. Genuine candid behavior. Natural body language. Unscripted slice-of-life feeling. Strong environmental authenticity. Rich real-world details and believable human motion. Camera Style: Early-2000s consumer DV camcorder aesthetic. Friend casually recording everyday moments. Heavy handheld shake, imperfect framing, frequent autofocus hunting, lens breathing, exposure pumping when moving between sun and shade, occasional motion blur, subtle rolling shutter, mild digital compression artifacts, faded colors, soft contrast, slight sensor noise. No stabilization. No cinematic camera moves. No modern color grading. 00:00–00:02 Outside a small house entrance. She sits on a low concrete wall adjusting her ponytail with both hands raised. A light breeze moves loose strands of hair. She smiles naturally while the camera struggles to hold focus. 00:02–00:04 The camera follows her into a narrow alley lined with potted plants and concrete walls. She notices a stray cat approaching and crouches down. Framing drifts off-center as the operator tries to keep up. 00:04–00:06 She gently pets and feeds the cat. Autofocus repeatedly shifts between her face and the animal. Morning sunlight flickers through leaves overhead. 00:06–00:08 Small front yard beside her house. She hangs laundry on a clothesline while fabrics sway in the breeze. Exposure changes as clouds briefly pass overhead. 00:08–00:10 On a quiet terrace with a ceramic coffee cup. She sits comfortably watching the neighborhood, occasionally brushing hair behind her ear. Loose handheld side angle with natural camera drift. 00:10–00:12 Close side profile. Someone off-camera greets her. She turns, raises her hand, smiles warmly, and casually says, “Annyeong.” The camera catches the moment slightly late. 00:12–00:15 Walking slowly down a tree-lined residential lane holding her coffee cup. She notices the camera, gives a small genuine smile, then looks away and continues walking. Recording cuts abruptly to black mid-motion as if the camcorder was switched off. Audio: Natural ambient sound only — morning birds, distant motorcycles, light wind, leaves rustling, faint neighborhood chatter, cat sounds, footsteps on concrete, fabric moving on clotheslines, subtle residential ambience. No music. No sound design. No narration. Goal: Authentic Korean neighborhood life captured like a forgotten home video from the early 2000s — candid, imperfect, realistic, warm, and deeply believable.
クリエイティブ
映像プロンプト元投稿 ↗
氷原の巨大異星遺跡へ向かう探検隊SFショット
Here is the prompt I used for the video: A small expedition team crosses a frozen plain toward colossal alien ruins beneath flowing green and violet auroras. Black geometric towers rise from the snow, their surfaces interrupted by narrow cyan energy seams. The closest explorer carries a compact scanning device projecting a soft orange glow onto armored gloves. Windblown snow partially obscures the distant structures, emphasizing their immense scale. Mass Effect-inspired ancient civilization mystery, grounded military equipment, cinematic wide shot, deep blue night palette, realistic snow and metal textures
ビジュアル
映像プロンプト元投稿 ↗
白ガレージから砂漠へ展開する自動車CMトランジション
Create a continuous 10-second vertical 9:16 ultra-photorealistic CGI automotive commercial. 0–3s: Static first-person POV inside a pure white minimalist garage. Two male hands in black gloves appear. A metallic green widebody Porsche 911 stands at a front 3/4 angle. The right hand swipes left, sending the Porsche sliding off-screen. A bright orange Mercedes-AMG GT with black aerodynamic details rapidly enters from the right, overshoots, bounces back and stops. The left hand swipes left, removing the Mercedes. A glossy red 1969 Ford Mustang Fastback with black hood stripes, black sports wheels, wide tires and aggressive lowered suspension slides in from the right and locks into the same position. The right index finger points at the Mustang to select it. 3–5s: The camera pushes closer as the white garage physically transforms: floor panels fold outward, revealing golden sand; massive walls unfold like origami, exposing endless desert dunes; ceiling panels retract, revealing a clear blue sky. Bright sunlight illuminates the stationary Mustang. Camera performs a fast cinematic 180° orbit. 5–7s: Extreme close-up of the Mustang's front grille. Headlights illuminate, the powerful V8 engine starts with a deep roar, and the body vibrates. Camera rapidly tracks along the hood toward the exhaust and rear wheel. The rear tire spins violently, throwing sand backward. Suspension compresses as engine RPM rises. 7–10s: The Mustang launches explosively straight toward the camera, spraying sand behind it. Low frontal camera retreats rapidly, then dodges sideways as the car blasts past. Camera whips around into a fast 180° tracking orbit, revealing the side profile, rear lights and massive dust trail. Finally, the camera overtakes the speeding Mustang and captures a dramatic low front 3/4 hero shot against golden dunes and blue sky. Powerful V8 roar, hard brake, instant cut. Realistic physics, aggressive speed ramps, seamless transitions, cinematic motion blur, mechanical folding sounds, swipe whooshes, tire screeches and authentic engine audio. Preserve exact car identities, classic 1969 Mustang proportions, consistent colors and spatial continuity. No morphing, teleportation, extra objects or text.
ビジュアル
一致する映像プロンプトが見つかりません。