Veo AI Video Generator for Text and Image Prompts

Describe a scene or bring an image to guide its first frame. Create with Veo on face in hole using text to video and image to video, then choose the available duration, framing, and output settings before generating.

254/10000
Model
Parameters
Reopen this page to resume result checks. Confirmed failures are refunded automatically.
Required Credits89

Veo: from an idea to your next video

Scene descriptions with a motion brief

Use text to video to describe the subject, action, setting, and camera movement together. Veo offers a way to explore a shot from a written brief. Give the scene a clear direction and review the result for motion and visual details.

An image as the starting point

Use image to video when an existing picture should guide the shot. Describe how the subject or camera should move beyond that image. The reference helps establish the scene, while the generated motion still needs review.

Model settings you can inspect

Choose an enabled Veo version and use the duration, aspect ratio, and resolution options shown for it. Different versions can offer different combinations. The quote reflects the current selection so you can compare options before submitting.

Audio when the selected option supports it

Some Veo configurations include an audio option. Use it only when it is offered for the selected model and settings. Describe the desired sound when applicable, then review the actual soundtrack and visuals together.

Veo for your creative workflow

Product and campaign motion concepts

Explore how a product scene might look with a camera move or a simple action. Use an image when you already have the starting composition. Check product geometry, labels, and changes across frames before choosing a result for your campaign.

Social video ideas

Write a short scene with one subject and one main action. Choose a supported aspect ratio for the intended placement. A focused shot is easier to assess and refine than a prompt containing many unrelated events.

Storyboard and shot exploration

Test the direction of a planned shot before building a full sequence. Specify framing, movement, and atmosphere. Compare the result with your storyboard; a generated clip is an exploration rather than a guarantee of exact continuity.

Motion from a still image

Start with a picture and describe a restrained movement, such as a slow push toward the subject or a breeze through the scene. Inspect changes to the subject and background as the clip progresses.

How to use the Veo AI Video Generator

  1. Choose a starting mode

    Select Text to Video for a scene described in words. Select Image to Video and add a supported reference for an image-led shot. Choose an available Veo version from this model family.

  2. Write the shot and review its quote

    Describe the subject, action, setting, lighting, and camera movement. Select the duration, framing, resolution, and audio option offered by your model. Review the displayed credit cost before generating.

  3. Generate and inspect the clip

    Submit the request without signing up and review its status in history. Watch the completed clip for motion, subject changes, and audio where applicable. Download the result or revise the prompt for your next shot.

Write a clearer Veo prompt

Subject, action, and setting

Give the shot one central subject and a clear action. For example: “A cyclist passes a quiet cafe at sunrise. Warm light reflects on the windows. A smooth tracking shot follows the rider.” Keep separate scenes in separate requests.

Camera movement and framing

Specify a wide shot, close-up, or another framing choice, then describe a simple movement. Avoid contradictory camera directions. For image to video, explain how the shot should develop from the reference.

Review motion and sound

Check the clip from start to finish instead of judging only its first frame. When audio is supported and selected, describe the intended sound and review what was actually generated. Refine the next prompt around the issue you observed.

Veo questions, answered

Can I use the Veo AI video generator with text and images?

Yes, this page brings together text to video and image to video for the enabled Veo family. The selected model determines which quoted modes and settings are available. Image to video needs a supported reference image.

Does image to video mean uploading a video?

No. Image to video starts from a still image and generates a clip. This page does not provide video to video editing. Use the image picker for the reference and describe the motion you want.

How should I describe camera movement?

Name the framing and one main camera move, such as a slow push-in or a tracking shot. Describe the subject action separately. Keeping the movement specific helps you compare the clip with your intended shot.

What duration and resolution does Veo support here?

The available choices are displayed for your selected Veo version. They depend on the active model configuration and quote combinations. This page does not promise a duration or resolution that is absent from the generator.

Can Veo generate audio with my video?

Audio depends on the selected Veo version and its available settings. If an audio option is offered, select it and include the desired sound in your prompt where relevant. Review the generated soundtrack; audio is not guaranteed for every configuration.

How are credits calculated?

The displayed quote uses the selected model, mode, duration, resolution, and other supported options. Check the amount before submitting. Visit Pricing to compare available plans and credit purchases.

Where do completed videos appear?

After signing in, review completed clips in history or Assets. Open a result to play it and use the available download controls. You can revise your description or reference and submit a new request for another variation.

Can I request a refund for my purchase?

You can request a refund within 10 days of purchase if you have unused credits from that purchase and provide a clear reason, subject to our Refund Policy. If eligible, an unused purchase can be fully refunded; a partly used purchase is refunded in proportion to its remaining unused credits. Fully used purchases and free or promotional credits are not refundable.

Do credits expire or carry over?

Credit validity depends on the pack, subscription or promotion that issued them. Review the purchase terms and expiration dates in Settings > Credits. A renewal or new purchase does not extend older credits. Use credits before their stated expiration; do not assume unused subscription credits roll over indefinitely.

What happens to credits if generation fails?

Credits charged for a task that is confirmed as failed due to a system error are returned automatically. A task that is still processing has not yet been confirmed as failed. Check its status and your credit history before submitting again. If a confirmed failure still shows an unresolved charge, email support@faceinhole.app with the task ID.

Can I get credits back if I do not like the result?

AI results can vary, so a completed result that differs from your expectations is not automatically treated as a technical failure. Eligible completed image tasks can be submitted for credit refund review using the refund option where available; approval is required. For a video or another issue, contact support@faceinhole.app with the task ID and details. A credit refund returns credits, not money to your payment method.

How can I get help with billing or a generation?

Email support@faceinhole.app. For billing, include your account email and order ID; for generation, include the task ID, issue description and relevant screenshots. If you purchased as a guest, keep the original browser data and payment receipt so we can help locate the purchase.

Make your next video with Veo

Bring your idea to face in hole, choose your starting mode, and review the available settings before generating.

Create with Veo

00:12-00:15] Vlogger , Biu ! , , ; , , , THE END!

View prompt

[魔法笔街头魔法Vlog · 15秒 · 竖屏9:16] [风格] 实拍 + 扁平2D动漫贴纸合成,第一人称街头魔法Vlog。8K照片级细节,带有真实智能手机后置摄像头画面的质感;照片级城市与扁平卡通角色之间强烈的对比。一镜到底的手持手机拍摄。无剪辑。无场景切换。 [摄影] 全程原始未稳定手持手机镜头:行走时的抖动,轻微手臂摇晃,偶尔自动对焦搜索,真实曝光在明亮天空与建筑物阴影之间的变化,快速摆动时的轻微滚动快门果冻效应。自然的手机HDR色彩,柔和的现实色调。目标之间镜头以快速甩动平移跟随钢笔移动。 [光线] 黄昏晚些时候的阳光来自一个一致的方向;每个真实物体和每个动画角色都投下柔和的接触阴影,与该阳光匹配。 [场景] 连续走完一个韩国城市街区:开头头顶有高架地铁轨道,树荫人行道上有鸽子,路边有公交车道,更远处有公交车站长椅。生活化的日常街道,背景路人自然移动。 [钢笔 — 魔法法则] Vlogger的真实手(照片级,可见毛孔)握着一支黑色马克笔,始终在画面中 — 连接每个节拍的视觉引导。每次变形遵循相同序列:钢笔指向,Vlogger的声音说“Biu!”,蓝色手绘草图线条包裹目标,墨水扩散,目标变成活泼的扁平2D赛璐璐动漫角色,带有大胆的卡通轮廓 — 保持原始物体确切的大小、位置、速度、方向和透视,完全锚定在真实街道上。角色保持扁平贴纸阴影,从未被现实世界光线重新照明;它们触碰的一切都以真实物理反应。 [00:00-00:03] 在高架轨道下行走的第一人称视角。手举起马克笔进入画面,指向一辆经过的地铁列车。“Biu!” — 草图线条包裹一节车厢,一个小巧的漫画风格超级英雄用蛛丝线在列车上荡行,然后消失在拐角处。列车本身保持完全照片级,相同速度。 SFX: 列车隆隆声 + 马克笔呼啸声 + 小巧的英雄划过声。 [00:03-00:06] 钢笔向下甩动,镜头跟随,到人行道上的一只鸽子。“Biu!” — 鸽子变成可爱的手绘卡通鸟;它跳两次,拍翅膀,飞走留下小草图羽毛,这些羽毛溶解成墨水颗粒,向路边飘去。 SFX: 翅膀拍打声 + 纸质羽毛沙沙声。 [00:06-00:10] 钢笔跟随颗粒向上到公交车道,一辆城市公交车正在经过。“Biu!” — 快速草图轮廓覆盖公交车,它变成一个巨大的扁平2D橙色虎斑猫,保持公交车的确切大小、速度、方向和透视,平静地沿着公交车道踱步。它的耳朵抽动,尾巴摇摆,爪子落在柏油路上投下柔和的接触阴影。 SFX: 公交车引擎融化成巨型垫步脚步声 + 低沉的咕噜声。 [00:10-00:12] 钢笔甩向公交车站长椅,那里坐着一个女人。“Biu!” — 草图线条描摹她,同一个女人、相同姿势、相同比例被重绘成生动的动漫赛璐璐插图。她温暖地微笑并挥手一次;几颗漫画闪光粒子向上飘浮。 SFX: 快速草图涂鸦声 + 轻柔的闪光铃声。 [00:12-00:15] Vlogger停下脚步,用最后一声最大声的“Biu—!”,将马克笔旋转着甩向天空。镜头向上倾斜跟随旋转的钢笔,它画出一道蓝色墨水螺旋;墨水绽放,直到整个真实天空变成手绘动漫天空 — 赛璐璐阴影渐变,云朵带有大胆卡通轮廓,手绘太阳。照片级城市天际线在画面底部保持完全真实。一个小巧的手写“THE END!”涂鸦 — 屏幕上唯一的文字 — 在绘制的云朵中弹出,画面定格。 SFX: 尖锐的投掷呼啸声 + 扩散的水彩晕染声 + 毡笔吱吱声写下“THE END!”。

aesthetic: Raw 35mm handheld, high altitude sun haze. One unbroken

View prompt

aesthetic: Raw 35mm handheld, high altitude sun haze. One unbroken continuous tracking shot. No cuts. All real time. audio: Full constant jet engine roar, wind blast, no other sound. timeline: - 0-3s: Normal guy in baggy cargo shorts and flip flops is standing perfectly relaxed balancing on top of the wing of an F16 doing 350mph at 10,000 feet. - 3-7s: The pilot leans out of the canopy, gives a thumbs up towards the guy on the wing. The guy leans forward slightly, smiles and returns the thumbs up. - 7-12s: He does a completely casual, perfectly clean full backflip. No hands. He doesn't grab anything. Lands exactly back on the exact same spot on the wing. He doesn't even stumble. - 12-15s: He brushes a tiny bit of dust off his shorts. Gives a bored little thumbs up straight to the camera. Hard cut. quality: 8K photorealistic, correct fabric motion blur, natural physics, no uncanny valley, no artifacts.

Create a single continuous self-filmed vlog recorded on a handheld MiniDV

View prompt

Concept: "Morning Walk Routine" Create a single continuous self-filmed vlog recorded on a handheld MiniDV camcorder. The camera is always held by the girl, creating a natural first-person selfie perspective with subtle hand shake, realistic autofocus hunting, slight exposure changes, and authentic walking motion. No cuts, transitions, or cinematic shots. Visual Style: Soft early-2000s MiniDV look with gentle tape grain, natural colors, mild highlight bloom, realistic indoor and outdoor lighting, and no beauty filters or heavy color grading. Character: YEJI, a Korean female idol in her 20s with long black hair, fresh natural makeup, and a cheerful personality. She begins in cozy pastel pajamas, then changes into a stylish athletic hoodie, leggings, and white sneakers. Location: A cozy modern apartment leading to a quiet tree-lined neighborhood and nearby park on a bright morning. The vlog begins as YEJI wakes up, reaches for the camera beside her bed, smiles sleepily, and says, "Good morning... let's start the day together." She opens the curtains, stretches, washes her face, ties her hair, drinks a glass of water, and grabs a light breakfast while casually chatting to the camera. She walks to her room, quickly changes into her walking outfit, checks herself in the entryway mirror, ties her shoes, grabs her water bottle, and smiles. "Okay... let's go." She steps outside and begins her morning walk through peaceful streets and a green park, occasionally turning the camera toward the scenery before bringing it back to herself. Halfway through the walk she laughs, "Getting outside this early always makes me feel better." The vlog ends as she reaches a sunny spot in the park, waves at the camera, and says, "Thanks for coming with me. See you next time." She continues walking as the camera lowers naturally and the recording ends. Generation Requirements: One continuous realistic take with consistent identity, natural body movement, accurate object interactions, smooth lighting transitions, believable camera motion, and no AI artifacts, jump cuts, anatomy errors, or duplicated objects. The result should feel like a real personal morning vlog.

Seedance Creator Video 1048

View prompt

{ "video_prompt": { "reference_images": { "image_1": "Main character — lock face, skin tone, body type, long straight black hair, white sleeveless top, black fitted mini skirt, black pointed heels. Keep identity consistent throughout.", "image_2": "Storyboard sheet — follow shot pacing, framing, camera moves, lighting, 2000s mood only. Do not reproduce panels/text/grid." }, "style": { "format": "early 2000s MiniDV camcorder footage", "camera": "handheld, shaky, constant reframing, subject drifts to frame edge", "focus": "autofocus hunting/pulsing, lens breathing", "exposure": "unstable auto-exposure", "color": "faded, low-contrast, blown highlights, digital noise, interlaced look", "stabilization": "none, no modern color grade" }, "setting": { "location": "quiet Korean residential alley", "details": "concrete alley, low houses, clotheslines, potted plants, parked bikes, tangled wires, trees", "light": "soft overcast morning light" }, "duration_seconds": 15, "shots": [ { "id": 1, "action": "sits on stone steps, fixes hair, wind blows, smiles", "camera": "focus hunting/pulsing" }, { "id": 2, "action": "follows into alley, crouches to greet small toy poodle", "camera": "handheld crouch-follow" }, { "id": 3, "action": "waters potted plants by low wall, leaves sway", "camera": "shaky, refocusing" }, { "id": 4, "action": "leans on iron gate holding coffee, watches street", "camera": "loose side drift" }, { "id": 5, "action": "close-up, waves off-screen, says 'annyeong'", "camera": "half-beat delayed follow" }, { "id": 6, "action": "tracked walking, notices camera, smiles, cuts to black mid-motion", "camera": "slow follow" } ], "dialogue": "안녕 (only line, once)", "sound": "birdsong, wind, distant motorcycle, dog, coffee cup, footsteps, one 'annyeong', no music", "avoid": ["jitter", "warped limbs", "identity drift", "temporal flicker"] } }

EVENT: Professional racing team's pit stop preparation moments before lights

View prompt

EVENT: Professional racing team's pit stop preparation moments before lights out. PRIMARY SUBJECT: Chief mechanic. Late 40s. Focused. Minimal conversation. SESSION TIME: 3:00 PM. Bright race-day conditions. LOCATION: Pit lane. Garage. Grandstands. Crowd in distance. DOCUMENTARY CAMERA: Cinema vérité. Shoulder-mounted. Following mechanics. Quick reframing. Occasional blocked views. GARAGE PROGRESSION: Tire inspection. Engine temperature check. Driver enters cockpit. Final countdown. Car exits garage. AUDIO: Air guns. Radio communication. Engine revs. Crowd. Mechanics shouting. DOCUMENTARY REALISM: Nobody acknowledges the camera. Crew remains fully focused on work. Should resemble behind-the-scenes motorsport coverage rather than a commercial.

VFX & Titles

Create a premium cinematic character bible sheet for a martial artist named

View prompt

Create a premium cinematic character bible sheet for a martial artist named LEE. Use the uploaded character sheet as the strict visual reference for his exact face, body, proportions, hair, skin tone, yellow jumpsuit with black stripes, white shoes. Do not change his appearance.LAYOUT inspired by premium AAA character presentation boards. Clean white background overall.LEFT SIDE: Massive bold yellow brushstroke painted text LEE top left corner, rough expressive hand-painted brush font. Below it small text: MARTIAL ARTIST / NUNCHAKU SPECIALIST. One massive full height dynamic hero pose of Lee directly below — low fighting stance, nunchaku mid-swing creating a motion blur arc around him, yellow jumpsuit catching light, ink wash watercolor splash behind him only, soft grey and white Chinese ink painting texture radiating outward from behind his body fading into white, no box no frame, standing directly on the white https://t.co/HEXmu94Jtq: Section labeled TURNAROUND in small clean text. Three full body views standing on clean white: Front, Side, Back. Same character same outfit same proportions as reference. Below turnaround: small section labeled TRAINING EQUIPMENT with one clean illustration of nunchaku — black handles silver chain fully extended.RIGHT SIDE: Section labeled DETAILS in small clean text. Grid of four clean close-up panels: Face front, Face side profile, Eyes close-up, Nunchaku handle and chain detail. Below details: COLOR PALETTE row with four swatches — yellow, black, white, silver. Small tagline in bottom right corner in thin elegant font: BE WATER.OVERALL FEEL: Premium martial arts character bible, ink wash cultural aesthetic, yellow as the dominant accent color, minimal clean typography, lots of breathing room and white space, no excessive text no gibberish, cinematic cel-shaded 3D anime, semi-realistic CGI, hand-painted textures, digital painting feel, hard-edge brushwork, heavy shadows, not cartoon not Disney not Pixar, print ready.

Pitch-black night. A supercharged airboat tears through a flooded cypress

View prompt

Pitch-black night. A supercharged airboat tears through a flooded cypress swamp at impossible speed, desperately escaping through an ever-changing maze of narrow black-water channels. The engine screams, the giant rear propeller blasts hurricane-force spray, and the swamp feels alive, trying to destroy the boat. The camera never stops moving: aerial dives through the trees, ultra-low water-level chase shots, aggressive FPV beside the spinning propeller, overhead drone reveals, violent orbit shots, crash zooms, whip pans, and near-miss flybys inches from the hull. Every second raises the stakes. The driver drifts through impossibly tight gaps between ancient cypress trunks, narrowly misses submerged logs and hidden roots, blasts through dense reeds, jumps over floating debris, skims muddy banks, and threads collapsing wooden bridges while massive beams, splinters, and chains crash all around. The boat launches off natural wakes, lands hard already sideways, ricochets through impossible S-turns, and squeezes through gaps with only inches to spare as branches whip across the camera and walls of black water explode into the air. The final seconds become absolute chaos: towering fallen trees block the channel, the driver commits to impossible last-second maneuvers at full throttle, the airboat launches beneath collapsing structures while debris rains from above, then bursts into open water as a gigantic rooster tail erupts behind and the collapsing swamp seems to swallow the escape route. Style: IMAX-quality hyper-realism, relentless speed, escalating danger, physically accurate water physics, cinematic lighting, volumetric fog, crystal-clear action, dramatic camera movement, no slow motion, no text, no logos, no recognizable faces.

First-person cyclist, handlebars and front wheel flashing low in frame

View prompt

SUBJECTS: First-person cyclist, handlebars and front wheel flashing low in frame during drops and hard turns. Vendors, laundry, scooters, dogs, chickens, cars, and pedestrians erupt around the rider as sudden obstacles. ENVIRONMENT: Dense Brazilian hillside streets, painted concrete stairs, tight landings, tiled corners, hanging wires, murals, awnings, puddles, hot late afternoon light, deep alley shadows, city sprawling below. MOOD: Adrenaline, max chaos, and nonstop street speed with violent spatial intensity in every direction. COLOR LOGIC: Hyperreal Pop Look CAMERA DETAILS: 360 action-cam POV, horizon-stable but brutal, nonstop forward drive, minimal roll, heavy stair vibration, sharp side and rear parallax, full-sphere chaos, no release. TIMELINE: 0:00-0:03: POV freefalls down a steep stairwell. The front wheel punches over the first steps, bars jackhammer below frame, the whole sphere shuddering with every hit while a child lunges in from the left to yank a rolling soccer ball out of the rider's line and walls, rails, balconies, and faces whip past on both sides. Violent forward descent with brutal stair vibration. SFX: (city hum, distant funk beat, tire chatter, breath, rapid stair hits, frame rattle). Hard sun above, deep shadow pockets below. 0:03-0:05: POV slashes left across a tiny landing, skips a broken crate, and drops again as laundry cracks across the front hemisphere, shoulder missing painted concrete by inches while side-wrap onlookers recoil. Hard lateral shake, immediate snap back into the stair run. SFX: (cloth slap, skid, crowd shout, chain buzz, stair chatter). 0:05-0:08: POV hammers the next staircase as a stray dog cuts center frame and startled chickens burst upward from the side steps, wings flaring across the sphere. The rider flicks the bars, rear wheel skates loose, then needles between a fruit cart and handrail with almost no clearance while the sphere jitters from every stair impact. Fast vibrating continuous-shot chaos. SFX: (tire chirp, crate clack, wings flapping, squawks, paw skitter, stair thuds, bass from window, metal rattle). 0:08-0:10: POV blasts out of one stair run, skips across a short asphalt gap between two stair sections without slowing, slams the opposite curb, and drops straight into the next descending steps. Only once the rider is fully back on the stairs do horns burst behind while passing cars rip through the side wrap. Full-speed crossing with strong lateral parallax and zero release. SFX: (engine idle, tire buzz, chain rattle, curb thump, car horns behind). 0:10-0:13: POV keeps attacking the next stair section immediately after the asphalt gap, machine-gunning through two tight landings and another steep stepped lane, every hit punching a fresh jolt through the sphere as stacked homes, wires, and alley mouths curl around the viewer and the overlook rushes closer. Forward lunge with impact drive and nonstop shake. SFX: (air rush, heavy thump, stair chatter, horn echo fading, chain lash, wind buffeting). 0:13-0:15: POV rips through the final stepped approach to the overlook and throws the rear wheel into a savage sideways skid, dust and gravel spraying across the lower frame while stair-lined drops fall away to both sides and the skyline blooms around the entire sphere in one fast violent sweep. The bike stays hot through the slide as the city fills every direction. SFX: (rear tire screech, gravel spray, freewheel spin, city roar, music drop).

Two elite urban climbers standing on the upper spire of Empire State

View prompt

Main Subject: Two elite urban climbers standing on the upper spire of Empire State Building, ~1,450 ft above Manhattan. Male climber: mid-20s to early 30s, athletic, matte-black technical shell jacket, black tactical cargo pants, climbing harness, gloves, compact utility backpack, black boots. Female climber: early to mid-20s, slim athletic build, matte-black insulated shell jacket, tactical pants, climbing harness, gloves, black boots. Hair tightly tied back, loose strands whipping in the wind. Realistic skin texture, authentic proportions, visible facial tension from altitude and cold wind. Maintain identical identity, clothing, and proportions throughout. Location: Upper antenna platform of the Empire State Building during blue-hour sunrise in New York City. Vast Manhattan skyline below with glowing city lights through cool haze. Visible skyscrapers, bridges, roads, tiny traffic lights, rooftop details, and distant fog. Steel beams, ladders, cables, bolts, and red aviation lights surround them. No crowds, helicopters, or nearby activity—only extreme altitude and isolation. Visual Style: Ultra-realistic documentary danger realism. Genuine unscripted stunt footage. Strong scale contrast between tiny humans and massive skyscraper geometry. Believable altitude physics, intense vertigo, raw viral social-media realism. Must feel like accidental real footage. Camera Style: High-end aerial drone + handheld action camera hybrid. Slight handheld instability from wind turbulence, subtle drone micro-corrections, minor vibration, occasional autofocus breathing, natural rolling shutter, realistic exposure shifts between sky and city lights. Minimal grading, natural dynamic range. Shot Breakdown 00:00–00:03 Extreme ultra-wide aerial shot of the Empire State Building from far away. Camera rapidly pushes toward the upper spire through cold morning air. Climbers appear as tiny black dots; viewer slowly realizes they are human. Wind causes subtle camera instability. 00:03–00:06 Camera moves closer, revealing both climbers on a narrow steel ledge barely wider than their boots. Jackets whip violently in strong wind. Female grips a steel cable for balance. Male slowly turns toward her. Manhattan fills the background below. 00:06–00:09 POV downward shot from the ledge toward streets below. Boots stand inches from the edge. Traffic looks microscopic like glowing particles. Slight body sway creates extreme vertigo. Wind vibration shakes camera. 00:09–00:12 Side tracking close shot circling them. Male reaches into jacket pocket and pulls out a small ring box. Female notices and freezes in confusion. Wind intensifies. Her breathing changes. 00:12–00:15 Close handheld documentary shot. Male carefully kneels on the steel ledge and opens the ring box. Female covers her mouth in shock, eyes watering. Hair whips across her face. She cries and smiles simultaneously. Recording ends abruptly mid-motion for raw authenticity. Audio: Natural environmental sound only—violent wind gusts, vibrating cables, steel creaks, distant city ambience, fabric flapping, breathing, nervous laughter, emotional gasps. No music or narration. Goal: Authentic viral Empire State Building proposal footage with terrifying scale, extreme altitude, emotional payoff, intense vertigo, and raw documentary realism indistinguishable from genuine footage.

A fast paced 15 second hyper realistic action video in 16 by 9 aspect ratio

View prompt

A fast paced 15 second hyper realistic action video in 16 by 9 aspect ratio driven by energetic electronic drum and bass music. The scene opens with a tight close up of a lush green potted bonsai tree on a florist counter. A hand swiftly grabs the pot. Cut to a dynamic handheld tracking shot following a young athletic woman wearing a bright yellow windbreaker and dark fitted athletic pants. She bursts out of the flower shop and breaks into a full speed sprint down a busy Seattle sidewalk. The camera shakes realistically to match her intense footfalls. She effortlessly vaults over a concrete planter and slides beneath a metal delivery cart. The lighting is cinematic midday sunlight creating high contrast shadows and bright lens flares bouncing off glass skyscrapers. Cut to a low angle shot pointing upward as she sprints underneath a moving elevated monorail train. The camera movement is frantic and urgent. She dashes up a set of steep stone stairs taking them three at a time. The frantic action suddenly cuts to a perfectly still calm static shot inside a sleek modern corporate office. The woman gently places the intact bonsai tree onto a polished glass desk in front of a stunned executive. Her breathing is slightly heavy but her expression is completely casual. The video must look entirely photorealistic with natural motion blur and authentic urban textures.

Seedance Creator Video 1137

View prompt

严格按参考分镜顺序制作,不要把整张网格当成一张图。每个面板都是独立镜头,生成一段15秒、手持手机自拍感的韩国情侣旅行 Vlog。 男生长相参考@@@,女生长相参考@@@。全程严格保持两人的脸、发型、穿搭、身材比例和情侣关系一致,不换脸、不变人。 视频像旧 iPhone 随手拍下的私人旅行记录:轻微晃动、偶尔失焦、自然变焦、运动模糊、镜头拉丝、曝光变化和不完美构图。不要广告感、电影感或过度稳定。 内容按旅程自然推进:出发、白天游玩、吃东西、牵手散步、互相拍照、打闹、看风景,最后在夜晚街道、车内或房间温馨收尾。 甜蜜感要自然,不刻意摆拍。加入回头等对方、拉衣袖、分享食物、整理头发、靠肩、牵手、笑着躲镜头、互相看对方等细节,让人看完很羡慕。 可穿插路人、街景、车窗、食物、手部、背影、侧脸、影子和环境细节。人物不要一直看镜头,要有真实聊天、笑声和自然互动。 整体质感:低对比度、轻微褪色、自然光、真实噪点、旧手机画质、温柔韩剧情侣日常氛围。 BGM为温馨轻快的韩剧恋爱 Vlog 风格,保留风声、脚步声、街道声、海浪声、餐具声和自然笑声。 禁止字幕、文字、水印、Logo、拼贴边框、静态照片轮播、夸张亲密动作、机械摆拍、CGI和商业旅拍感。

· Updated

What's new on this page

  • — Updated model selection with searchable brand menus on desktop and a flat model list in a mobile bottom sheet.
  • — Added editable example prompts and separate drafts for text and reference modes, with an action to restore the example.
  • — Updated page copy and content.
  • — Page content published.