RapLyrics
PricingLog in / Sign Up
Black Friday · Up to 30% off
21Days02Hours05Min35Sec
View deals →

HomeHOTLyric Video Prompts

AI Generations

AI VideoAI Image

Models

Veo AI VideoKling AI VideoBanana AI Image

Assets LibraryFavorites
Upgrade Plan
RapLyrics
  1. Home
  2. AI Video Maker
  3. Seedance 2.5

Seedance Video Scenes for Music Visuals

Bring Your Creative Vision to Life

Check the model selector for current availability, supported inputs and credit costs. This page is configured for Seedance 2.5. Published examples are creative references; inspect each case for the model that created it.

Create with Seedance 2.5
Online Use
Text and Image Inputs
Optional Audio Settings
Review Motion in Every Clip
Online Use
Text and Image Inputs
Optional Audio Settings
Review Motion in Every Clip

AI Video Generator

Loading video models…

254/10000
Required Credits—
Reopen this page to resume result checks. Confirmed failures are refunded automatically.
1 / 12
Seedance Creator Video 496
Verified prompt

3:2 横版,电影级写实人像近景特写,一位年轻成年东方女性,视觉年龄约 22–25 岁,明确成年,原创人物,不复刻具体明星脸。人物拥有小巧流畅的鹅蛋脸,清亮圆杏眼,深棕色瞳孔,眼神安静、惊讶、克制,像刚刚在画外看见一个多年未见的重要旧人。瞳孔轻微放大,上眼睑微微抬起,下眼睑轻度收紧,眼睛里有清晰自然的高光和轻微湿润感,视线看向镜头右侧画外。 眉形自然柔和,保留真实眉毛毛流;鼻梁细直,鼻尖小巧自然;嘴唇微微张开,露出极少量牙齿,唇色为低饱和豆沙粉,嘴角没有明显笑意,表情介于惊讶、怀念与不敢确认之间。面部表情细腻克制,不夸张,不哭泣,不摆拍。 皮肤白皙自然,保留真实毛孔、轻微细纹、细小绒毛、鼻翼与脸颊的细微肤色变化,面部有少量自然小瑕疵,不过度磨皮,不塑料皮肤,不假面感。脸颊有极轻微自然红润,眼周和鼻尖受到柔和光线照亮。 黑色长发低束在脑后,发型自然松散,脸侧有数缕被微风吹起的细碎发丝,其中一缕横过脸颊与鼻梁,增强真实动态感。人物围着浅米白色柔软围巾,穿浅色外套,只露出肩颈以上,服装质感柔软朴素,符合秋冬城市夜晚。 夜晚城市街头,背景完全虚化,只有少量暖白色路灯光斑、灰蓝色暗部 and 模糊城市环境,环境不抢人物。柔和冷暖混合城市环境光从侧前方照亮人物面部,眼睛高光自然,另一侧脸部保留轻微阴影,曝光克制,暗部有层次。 超近距离人像摄影,85mm 电影人像镜头,f/1.4 浅景深,眼睛精准对焦,面部边缘自然柔化,真实摄影机成像,高动态范围,低饱和冷中性色彩,轻微电影胶片颗粒,安静、含蓄、带故事感的亚洲文艺电影画面,照片级真实,细腻自然,高级电影剧照质感。 负面约束:不要卡通,不要插画,不要 3D CG,不要网红脸,不要欧美化,不要幼态未成年感,不要浓妆,不要假睫毛过重,不要磨皮过度,不要塑料皮肤,不要脸部过亮,不要五官失真,不要眼睛大小不一致,不要瞳孔异常,不要夸张流泪,不要大笑,不要强烈表演感,不要杂乱背景,不要霓虹灯污染,不要过度锐化,不要 AI 蜡像感。

3:2 横版,电影级写实人像近景特写,一位年轻成年东方女性,视觉年龄约 22–25 岁,明确成年,原创人物,不复刻具体明星脸。人物拥有小巧流畅的鹅蛋脸,清亮圆杏眼,深棕色瞳孔,眼神安静、惊讶、克制,像刚刚在画外看见一个多年未见的重要旧人。瞳孔轻微放大,上眼睑微微抬起,下眼睑轻度收紧,眼睛里有清晰自然的高光和轻微湿润感,视线看向镜头右侧画外。 眉形自然柔和,保留真实眉毛毛流;鼻梁细直,鼻尖小巧自然;嘴唇微微张开,露出极少量牙齿,唇色为低饱和豆沙粉,嘴角没有明显笑意,表情介于惊讶、怀念与不敢确认之间。面部表情细腻克制,不夸张,不哭泣,不摆拍。 皮肤白皙自然,保留真实毛孔、轻微细纹、细小绒毛、鼻翼与脸颊的细微肤色变化,面部有少量自然小瑕疵,不过度磨皮,不塑料皮肤,不假面感。脸颊有极轻微自然红润,眼周和鼻尖受到柔和光线照亮。 黑色长发低束在脑后,发型自然松散,脸侧有数缕被微风吹起的细碎发丝,其中一缕横过脸颊与鼻梁,增强真实动态感。人物围着浅米白色柔软围巾,穿浅色外套,只露出肩颈以上,服装质感柔软朴素,符合秋冬城市夜晚。 夜晚城市街头,背景完全虚化,只有少量暖白色路灯光斑、灰蓝色暗部 and 模糊城市环境,环境不抢人物。柔和冷暖混合城市环境光从侧前方照亮人物面部,眼睛高光自然,另一侧脸部保留轻微阴影,曝光克制,暗部有层次。 超近距离人像摄影,85mm 电影人像镜头,f/1.4 浅景深,眼睛精准对焦,面部边缘自然柔化,真实摄影机成像,高动态范围,低饱和冷中性色彩,轻微电影胶片颗粒,安静、含蓄、带故事感的亚洲文艺电影画面,照片级真实,细腻自然,高级电影剧照质感。 负面约束:不要卡通,不要插画,不要 3D CG,不要网红脸,不要欧美化,不要幼态未成年感,不要浓妆,不要假睫毛过重,不要磨皮过度,不要塑料皮肤,不要脸部过亮,不要五官失真,不要眼睛大小不一致,不要瞳孔异常,不要夸张流泪,不要大笑,不要强烈表演感,不要杂乱背景,不要霓虹灯污染,不要过度锐化,不要 AI 蜡像感。

16:9
Cinematic high-energy multi-shot video, 15 rapid dynamic shots telling a #550350
Verified prompt

Cinematic high-energy multi-shot video, 15 rapid dynamic shots telling a complete story, fast-paced urban bike courier race against the clock through rainy neon city streets, consistent young woman in her mid-20s, short wavy dark hair in a high ponytail, light olive skin, freckles, determined focused expression turning to triumphant relief, black waterproof cycling jacket over gray hoodie, cargo pants, reflective backpack, realistic detailed face and hands, vibrant wet-street neon reflections, rain, steam from manholes, bustling night traffic atmosphere. Shot 1: Extreme close-up on phone screen flashing “Delivery deadline: 15 min – Critical medical package”, she snaps her head up in a small cluttered apartment hallway, eyes wide, grabs the sealed insulated bag and helmet. Handheld urgent camera, tense electronic beat kicks in. Shot 2: Medium tracking shot from behind as the same young woman in her mid-20s with short wavy dark hair in high ponytail, black waterproof jacket, charges down dim stairwell carrying the package, boots echoing, heavy breathing. Shot 3: Quick cut to exterior wide shot of rain-soaked city street at night, neon signs glowing, she bursts out the building door, mounts a sleek black delivery bike, pedals hard into traffic. Shot 4: Dynamic over-the-shoulder medium shot following her weaving between cars and buses, ponytail whipping, rain streaking across visor, fast dolly with colorful neon reflections on wet asphalt. Shot 5: Low-angle close-up alternating between spinning bike wheels splashing through puddles and her focused face checking the phone map, sweat and rain on forehead, shallow depth of field, rhythmic pedaling and rain SFX. Shot 6: Fast tracking shot as she cuts across a busy crosswalk just as lights change, package secure on back, dramatic lens flares from headlights and neon. Shot 7: Medium side shot, she skids to a stop outside a glowing hospital entrance, dismounts in one fluid motion, intense focus, first door-slam sounds. Shot 8: POV from her hands rapidly scanning QR code and handing the sealed bag to a waiting nurse, slight handheld shake, rain dripping, urgent but controlled audio. Shot 9: Cut to her face, the same young woman in her mid-20s with short wavy dark hair in high ponytail, black jacket, sudden smile of relief as the nurse nods and rushes inside, quick push-in. Shot 10: Wide orbiting shot around her as she mounts the bike again under the hospital canopy lights, rain still falling, city lights reflecting, music lifting. Shot 11: Extreme long shot from above showing the neon city stretching out while she rides away, breathing hard but grinning, headlights streaking. Shot 12: Close-up on her hands gripping the handlebars and phone now showing “Delivered – On time”, water droplets flying, focused triumphant grin, satisfying notification chime. Shot 13: Medium shot from behind as she coasts through a quieter side street, neon still bathing the scene, first relaxed posture, warm color grading intensifies. Shot 14: Slow-motion close-up on her face as she removes the helmet, rain mixing with sweat, pure joy and exhaustion, eyes sparkling under streetlights, music peaking with distant city hum. Shot 15: Final wide pull-out shot of her riding confidently into the glowing rainy night city, satisfied laugh, ambient traffic and rain sounds, fade out on energetic neon atmosphere.

Cinematic high-energy multi-shot video, 15 rapid dynamic shots telling a complete story, fast-paced urban bike courier race against the clock through rainy neon city streets, consistent young woman in her mid-20s, short wavy dark hair in a high ponytail, light olive skin, freckles, determined focused expression turning to triumphant relief, black waterproof cycling jacket over gray hoodie, cargo pants, reflective backpack, realistic detailed face and hands, vibrant wet-street neon reflections, rain, steam from manholes, bustling night traffic atmosphere. Shot 1: Extreme close-up on phone screen flashing “Delivery deadline: 15 min – Critical medical package”, she snaps her head up in a small cluttered apartment hallway, eyes wide, grabs the sealed insulated bag and helmet. Handheld urgent camera, tense electronic beat kicks in. Shot 2: Medium tracking shot from behind as the same young woman in her mid-20s with short wavy dark hair in high ponytail, black waterproof jacket, charges down dim stairwell carrying the package, boots echoing, heavy breathing. Shot 3: Quick cut to exterior wide shot of rain-soaked city street at night, neon signs glowing, she bursts out the building door, mounts a sleek black delivery bike, pedals hard into traffic. Shot 4: Dynamic over-the-shoulder medium shot following her weaving between cars and buses, ponytail whipping, rain streaking across visor, fast dolly with colorful neon reflections on wet asphalt. Shot 5: Low-angle close-up alternating between spinning bike wheels splashing through puddles and her focused face checking the phone map, sweat and rain on forehead, shallow depth of field, rhythmic pedaling and rain SFX. Shot 6: Fast tracking shot as she cuts across a busy crosswalk just as lights change, package secure on back, dramatic lens flares from headlights and neon. Shot 7: Medium side shot, she skids to a stop outside a glowing hospital entrance, dismounts in one fluid motion, intense focus, first door-slam sounds. Shot 8: POV from her hands rapidly scanning QR code and handing the sealed bag to a waiting nurse, slight handheld shake, rain dripping, urgent but controlled audio. Shot 9: Cut to her face, the same young woman in her mid-20s with short wavy dark hair in high ponytail, black jacket, sudden smile of relief as the nurse nods and rushes inside, quick push-in. Shot 10: Wide orbiting shot around her as she mounts the bike again under the hospital canopy lights, rain still falling, city lights reflecting, music lifting. Shot 11: Extreme long shot from above showing the neon city stretching out while she rides away, breathing hard but grinning, headlights streaking. Shot 12: Close-up on her hands gripping the handlebars and phone now showing “Delivered – On time”, water droplets flying, focused triumphant grin, satisfying notification chime. Shot 13: Medium shot from behind as she coasts through a quieter side street, neon still bathing the scene, first relaxed posture, warm color grading intensifies. Shot 14: Slow-motion close-up on her face as she removes the helmet, rain mixing with sweat, pure joy and exhaustion, eyes sparkling under streetlights, music peaking with distant city hum. Shot 15: Final wide pull-out shot of her riding confidently into the glowing rainy night city, satisfied laugh, ambient traffic and rain sounds, fade out on energetic neon atmosphere.

9:16
Seedance Creator Video 790
Verified prompt

アザラシをモチーフにした小さなぬいぐるみ風の動物たちが、透明なオレンジゼリーの水族館で泳いでいるミニチュア世界。ぷるぷるの水槽、みかんのトンネル、クリームの泡、レモン色のライト。とても小さな黒い点目、控えめな表情、短い手足、400x736縦長の動画入力用。大きい目、光沢のある目、アニメ目は禁止。

アザラシをモチーフにした小さなぬいぐるみ風の動物たちが、透明なオレンジゼリーの水族館で泳いでいるミニチュア世界。ぷるぷるの水槽、みかんのトンネル、クリームの泡、レモン色のライト。とても小さな黒い点目、控えめな表情、短い手足、400x736縦長の動画入力用。大きい目、光沢のある目、アニメ目は禁止。

25:46
Montage, multi-shot Hollywood action blockbuster, photorealistic, ARRI ALEXA
Verified prompt

Montage, multi-shot Hollywood action blockbuster, photorealistic, ARRI ALEXA aesthetic, anamorphic lenses, cinematic lighting, film grain, professional color grading, high detail stone and skin texture, no 3D render look, no cartoon, 15 seconds. <<Image 1>> — the heroine's base appearance and outfit. <<Image 2>> — glowing accents. stone monster reference: four of these creatures, cracked granite bodies with molten orange glowing eyes and fissures. Setting: vast ancient temple hall, towering carved columns, a low stone pedestal in the center, dust and floating embers in shafts of cold moonlight from above, warm firelight from braziers. Shot 1 (0–2.5s): God's-eye top-down view of the entire hall. The girl from <<Image 1>> stands on the pedestal at dead center, a small sphere of golden light pulsing in her raised hand. Four stone monsters charge toward her from four directions between the columns, their heavy footsteps cracking the floor tiles. Camera plunges straight down toward her in a slow corkscrew spiral. Shot 2 (2.5–4.5s): Low angle from the floor behind her shoulder. The nearest monster is already mid-swing, its massive stone fist crashing down toward her. She looks up at it and shouts sharply, defiant and provoked — low fierce chest voice, a battle-cry delivery, not conversational: "Okay, you asked for it." On the last word the orb detonates into a golden shockwave — the attacking monster is hurled backward along the blast direction, slamming into a column that cracks and sheds debris. Shot 3 (4.5–7.5s): Slow low-angle orbit around the pedestal. Golden light spirals up around her body, lifting her off the ground. The transformation happens UNDER FIRE: two monsters lunge at her simultaneously, claws raking against the sphere of light, sparks and stone chips flying, the barrier flexing under each hit. Her clothes dissolve into light and reform as the white knight armor with orange accents from . A golden spear materializes in her hand. Shot 4 (7.5–10.5s): She hovers a few meters above the monsters. A monster leaps at her from behind — fast whip-pan following its leap. She pivots mid-air, spins the spear once and drives it through the creature's chest. The monster is launched along the exact direction of the spear thrust, shattering into glowing rubble against the far wall. Impact physics: the body travels along the strike vector, not a generic sideways knockback. Shot 5 (10.5–13s): Camera tracks forward THROUGH the falling glowing debris of the destroyed monster, revealing the two remaining creatures already charging her. She dives down in a sweeping arc, the spinning spear carving a crescent wave of golden energy — the second monster is cut apart mid-charge, its chunks flying along the arc of the strike. Destroyed monsters stay destroyed, never reassemble. Shot 6 (13–15s): Extreme low Dutch angle from floor level. The last monster is mid-leap above her. Brief speed-ramp slow motion as she thrusts the spear down through it and impales it into the temple floor — golden cracks explode outward across the tiles. She then says in a low, firm voice: "I warned you."Normal speed: she lands lightly in the settling stone dust and embers, armor glowing, spear planted. Audio: heavy stone footsteps, granite cracking, deep monster roars, resonant energy hum, spear whoosh, thunderous impacts, no music. Constraints: monsters never stand idle or wait — they attack continuously throughout every shot, including during the transformation. Destroyed monsters do not return or reform. One camera movement per shot. Avoid jitter, no bent limbs, no facial deformation, preserve the heroine's face from <<Image 1>> in both forms.

Montage, multi-shot Hollywood action blockbuster, photorealistic, ARRI ALEXA aesthetic, anamorphic lenses, cinematic lighting, film grain, professional color grading, high detail stone and skin texture, no 3D render look, no cartoon, 15 seconds. <<Image 1>> — the heroine's base appearance and outfit. <<Image 2>> — glowing accents. stone monster reference: four of these creatures, cracked granite bodies with molten orange glowing eyes and fissures. Setting: vast ancient temple hall, towering carved columns, a low stone pedestal in the center, dust and floating embers in shafts of cold moonlight from above, warm firelight from braziers. Shot 1 (0–2.5s): God's-eye top-down view of the entire hall. The girl from <<Image 1>> stands on the pedestal at dead center, a small sphere of golden light pulsing in her raised hand. Four stone monsters charge toward her from four directions between the columns, their heavy footsteps cracking the floor tiles. Camera plunges straight down toward her in a slow corkscrew spiral. Shot 2 (2.5–4.5s): Low angle from the floor behind her shoulder. The nearest monster is already mid-swing, its massive stone fist crashing down toward her. She looks up at it and shouts sharply, defiant and provoked — low fierce chest voice, a battle-cry delivery, not conversational: "Okay, you asked for it." On the last word the orb detonates into a golden shockwave — the attacking monster is hurled backward along the blast direction, slamming into a column that cracks and sheds debris. Shot 3 (4.5–7.5s): Slow low-angle orbit around the pedestal. Golden light spirals up around her body, lifting her off the ground. The transformation happens UNDER FIRE: two monsters lunge at her simultaneously, claws raking against the sphere of light, sparks and stone chips flying, the barrier flexing under each hit. Her clothes dissolve into light and reform as the white knight armor with orange accents from . A golden spear materializes in her hand. Shot 4 (7.5–10.5s): She hovers a few meters above the monsters. A monster leaps at her from behind — fast whip-pan following its leap. She pivots mid-air, spins the spear once and drives it through the creature's chest. The monster is launched along the exact direction of the spear thrust, shattering into glowing rubble against the far wall. Impact physics: the body travels along the strike vector, not a generic sideways knockback. Shot 5 (10.5–13s): Camera tracks forward THROUGH the falling glowing debris of the destroyed monster, revealing the two remaining creatures already charging her. She dives down in a sweeping arc, the spinning spear carving a crescent wave of golden energy — the second monster is cut apart mid-charge, its chunks flying along the arc of the strike. Destroyed monsters stay destroyed, never reassemble. Shot 6 (13–15s): Extreme low Dutch angle from floor level. The last monster is mid-leap above her. Brief speed-ramp slow motion as she thrusts the spear down through it and impales it into the temple floor — golden cracks explode outward across the tiles. She then says in a low, firm voice: "I warned you."Normal speed: she lands lightly in the settling stone dust and embers, armor glowing, spear planted. Audio: heavy stone footsteps, granite cracking, deep monster roars, resonant energy hum, spear whoosh, thunderous impacts, no music. Constraints: monsters never stand idle or wait — they attack continuously throughout every shot, including during the transformation. Destroyed monsters do not return or reform. One camera movement per shot. Avoid jitter, no bent limbs, no facial deformation, preserve the heroine's face from <<Image 1>> in both forms.

16:9
Stylized 3D animation, Pixar-meets-horror render quality (think the polish
Verified prompt

[STYLE] Stylized 3D animation, Pixar-meets-horror render quality (think the polish of a feature film with a darker palette). Subsurface-scattering skin, soft global illumination, physically based materials. Lighting: single red safelight as the key, deep red-to-black falloff, volumetric red haze. Color palette: blood red, warm amber rim light, ink-black shadows. Quality: clean high-fidelity render, ray-traced reflections in the developer trays, fine grain overlay for mood. Mood: creeping realization, uncanny stillness. Pacing: methodical build, gut-drop ending. Aspect ratio 2.39:1. [CONSTRAINTS] Change camera angle every cut. Keep the man's character model and the darkroom identical across all shots — the only change is the figure inside each developing photo growing nearer. Animation must stay readable: clear silhouettes, weighted movement, no floaty motion. Same shirt, glasses, room, and prop placement throughout. No dialogue; breath and darkroom SFX only; no music until the sting. No text/logos/watermarks. [CHARACTERS / SUBJECT] Man, 40s, stylized-realistic proportions (slightly heightened features, believable build). Round glasses, rolled-up shirt sleeves, tired posture. Materials: soft fabric shader on the shirt, subsurface skin, light stubble. Personality: rational, skeptical, slowly unraveling. Movement style: deliberate and grounded early, hands growing shaky as dread builds. Emotional state: calm curiosity sliding into horror, shown through facial rig — brow, eyes, jaw. [SETTING] Basement darkroom, night. Red safelight bulb, a wire line of hanging prints, enamel developing trays with rippling liquid, glass chemical bottles catching red highlights. Background: a black open doorway behind him, held just out of focus. Environmental detail: floating dust in the safelight beam, faint condensation, worn concrete floor. [SCENE] Beginning: he develops a roll of old family film. Main action: a figure appears in the background of each print. Turn: with every new photo, the figure is closer to his family. Ending: the final print shows it standing directly behind them — meaning directly behind him — and he hears it breathe. [CUTS] cut1: Macro close-up, image surfacing in developer fluid, ripples distorting the red reflection. SFX: liquid swish, safelight hum. cut2: Over-the-shoulder, he lifts the dripping print: family on a sunny lawn, a tiny dark figure far back in the trees. SFX: fluid drips, soft breath. cut3: Wide low-angle of him pinning prints to the line, unaware, the dark doorway looming behind. SFX: clothespin snap, room tone. cut4: Insert macro on the second print — the figure now mid-lawn, clearly closer, features still hidden. SFX: a single heartbeat enters. cut5: Tight on his face in red light, glasses catching the glow, brow tightening. SFX: ambience thins toward silence. cut6: Top-down on the final print developing in the tray — the figure standing right behind the family group. SFX: a slow exhale that isn't his. cut7: Whip to a low push-in as he turns; the safelight sways and the doorway is empty, but a dark shape smears across the frame edge. VFX/SFX: string sting, safelight flicker, one motion-blur pass. [SOUND DIRECTION] Safelight electrical hum, liquid swish, and drips run throughout. A single heartbeat builds from cut4. One breath cue at cut6, one orchestral sting at cut7. No continuous music. [VFX] Volumetric red light bloom, drifting chemical haze in the beam, ray-traced ripple reflections in the tray, a single motion-blur pass on the closing shape. Keep it controlled — nothing flashy. [NEGATIVE GUIDANCE] No text on screen, no logos, no watermark, no dead-eyed or melted faces, no broken rig or anatomy, no floaty weightless motion, no style mismatch between shots, no inconsistent character model or room, no plastic-looking skin, no figure that reads differently between photos, no unreadable camera, no modern tech.

[STYLE] Stylized 3D animation, Pixar-meets-horror render quality (think the polish of a feature film with a darker palette). Subsurface-scattering skin, soft global illumination, physically based materials. Lighting: single red safelight as the key, deep red-to-black falloff, volumetric red haze. Color palette: blood red, warm amber rim light, ink-black shadows. Quality: clean high-fidelity render, ray-traced reflections in the developer trays, fine grain overlay for mood. Mood: creeping realization, uncanny stillness. Pacing: methodical build, gut-drop ending. Aspect ratio 2.39:1. [CONSTRAINTS] Change camera angle every cut. Keep the man's character model and the darkroom identical across all shots — the only change is the figure inside each developing photo growing nearer. Animation must stay readable: clear silhouettes, weighted movement, no floaty motion. Same shirt, glasses, room, and prop placement throughout. No dialogue; breath and darkroom SFX only; no music until the sting. No text/logos/watermarks. [CHARACTERS / SUBJECT] Man, 40s, stylized-realistic proportions (slightly heightened features, believable build). Round glasses, rolled-up shirt sleeves, tired posture. Materials: soft fabric shader on the shirt, subsurface skin, light stubble. Personality: rational, skeptical, slowly unraveling. Movement style: deliberate and grounded early, hands growing shaky as dread builds. Emotional state: calm curiosity sliding into horror, shown through facial rig — brow, eyes, jaw. [SETTING] Basement darkroom, night. Red safelight bulb, a wire line of hanging prints, enamel developing trays with rippling liquid, glass chemical bottles catching red highlights. Background: a black open doorway behind him, held just out of focus. Environmental detail: floating dust in the safelight beam, faint condensation, worn concrete floor. [SCENE] Beginning: he develops a roll of old family film. Main action: a figure appears in the background of each print. Turn: with every new photo, the figure is closer to his family. Ending: the final print shows it standing directly behind them — meaning directly behind him — and he hears it breathe. [CUTS] cut1: Macro close-up, image surfacing in developer fluid, ripples distorting the red reflection. SFX: liquid swish, safelight hum. cut2: Over-the-shoulder, he lifts the dripping print: family on a sunny lawn, a tiny dark figure far back in the trees. SFX: fluid drips, soft breath. cut3: Wide low-angle of him pinning prints to the line, unaware, the dark doorway looming behind. SFX: clothespin snap, room tone. cut4: Insert macro on the second print — the figure now mid-lawn, clearly closer, features still hidden. SFX: a single heartbeat enters. cut5: Tight on his face in red light, glasses catching the glow, brow tightening. SFX: ambience thins toward silence. cut6: Top-down on the final print developing in the tray — the figure standing right behind the family group. SFX: a slow exhale that isn't his. cut7: Whip to a low push-in as he turns; the safelight sways and the doorway is empty, but a dark shape smears across the frame edge. VFX/SFX: string sting, safelight flicker, one motion-blur pass. [SOUND DIRECTION] Safelight electrical hum, liquid swish, and drips run throughout. A single heartbeat builds from cut4. One breath cue at cut6, one orchestral sting at cut7. No continuous music. [VFX] Volumetric red light bloom, drifting chemical haze in the beam, ray-traced ripple reflections in the tray, a single motion-blur pass on the closing shape. Keep it controlled — nothing flashy. [NEGATIVE GUIDANCE] No text on screen, no logos, no watermark, no dead-eyed or melted faces, no broken rig or anatomy, no floaty weightless motion, no style mismatch between shots, no inconsistent character model or room, no plastic-looking skin, no figure that reads differently between photos, no unreadable camera, no modern tech.

16:9
An animated young girl tries to apply makeup for a special dinner. She
Verified prompt

An animated young girl tries to apply makeup for a special dinner. She attempts two different looks but each one turns out messy and unnatural. Frustrated, she wipes everything off and gives up. Wearing a cozy oversized sweater, she casually applies a tiny bit of blush and lip balm without thinking, creating the perfect natural look. She looks into the mirror in surprise, changes into an elegant casual outfit, smiles confidently, and happily walks out to meet her friends. Pixar-style 3D animation, cinematic lighting, expressive facial animation, warm emotional storytelling, detailed cozy bedroom environment.

An animated young girl tries to apply makeup for a special dinner. She attempts two different looks but each one turns out messy and unnatural. Frustrated, she wipes everything off and gives up. Wearing a cozy oversized sweater, she casually applies a tiny bit of blush and lip balm without thinking, creating the perfect natural look. She looks into the mirror in surprise, changes into an elegant casual outfit, smiles confidently, and happily walks out to meet her friends. Pixar-style 3D animation, cinematic lighting, expressive facial animation, warm emotional storytelling, detailed cozy bedroom environment.

3:4
second high-intensity motorcycle commercial, ultra cinematic, aggressive
Verified prompt

15-second high-intensity motorcycle commercial, ultra cinematic, aggressive editing style, perfectly synced to music beats, fast cut rhythm with explosive transitions, luxury performance motorcycle advertisement. Heavy use of speed ramping, whip pans, crash zooms, motion blur, and dynamic camera shakes for impact. Beat 1 (Intro Hit) Extreme close-up of motorcycle LED headlight turning on in total darkness, sudden light ignition, quick push-in with subtle lens flare burst. Beat 2 Rider puts on helmet, visor slams down, sharp sound-synced cut, tight close-up with slight camera shake for impact. Beat 3 (Build-up) Engine ignition close-up, mechanical vibration intensifies, fast orbit camera movement, metallic tension buildup. DROP 🔥 Beat 4 Motorcycle launches forward violently from standstill, tire grip explosion, dust burst, aggressive rear tracking shot with speed ramp. Beat 5 High-speed mountain drift through sharp corner, motorcycle leaning hard, drone whip-pan following movement, heavy motion blur, cinematic tension. Beat 6 Fast urban night sprint through real city streets, warm street lights, rapid FPV forward rush, crash zoom transitions between street sections, gritty realistic tone (no neon, natural lighting only). Beat 7 (Mid-air energy peak) Drone orbit shot around motorcycle crossing bridge at extreme speed, wind pressure visible, environment wide scale reveal, fast rotational camera movement. Beat 8 (Impact shot) Ultra-low roadside pass-by, motorcycle rushes past camera at extremely close distance, strong whoosh effect, heavy motion blur, slight camera shake impact. Beat 9 (Hero landing) Cinematic crane-up reveal at mountain overlook, golden hour sunset, motorcycle slowly settles, calm contrast after chaos, epic final hero frame. 🎬 Style Direction (Important) Ducati / BMW Motorrad / Top Gear cinematic aggression, Netflix automotive intensity, IMAX-scale realism, grounded physics, no cyberpunk, no neon, pure mechanical power + real-world adrenaline.

15-second high-intensity motorcycle commercial, ultra cinematic, aggressive editing style, perfectly synced to music beats, fast cut rhythm with explosive transitions, luxury performance motorcycle advertisement. Heavy use of speed ramping, whip pans, crash zooms, motion blur, and dynamic camera shakes for impact. Beat 1 (Intro Hit) Extreme close-up of motorcycle LED headlight turning on in total darkness, sudden light ignition, quick push-in with subtle lens flare burst. Beat 2 Rider puts on helmet, visor slams down, sharp sound-synced cut, tight close-up with slight camera shake for impact. Beat 3 (Build-up) Engine ignition close-up, mechanical vibration intensifies, fast orbit camera movement, metallic tension buildup. DROP 🔥 Beat 4 Motorcycle launches forward violently from standstill, tire grip explosion, dust burst, aggressive rear tracking shot with speed ramp. Beat 5 High-speed mountain drift through sharp corner, motorcycle leaning hard, drone whip-pan following movement, heavy motion blur, cinematic tension. Beat 6 Fast urban night sprint through real city streets, warm street lights, rapid FPV forward rush, crash zoom transitions between street sections, gritty realistic tone (no neon, natural lighting only). Beat 7 (Mid-air energy peak) Drone orbit shot around motorcycle crossing bridge at extreme speed, wind pressure visible, environment wide scale reveal, fast rotational camera movement. Beat 8 (Impact shot) Ultra-low roadside pass-by, motorcycle rushes past camera at extremely close distance, strong whoosh effect, heavy motion blur, slight camera shake impact. Beat 9 (Hero landing) Cinematic crane-up reveal at mountain overlook, golden hour sunset, motorcycle slowly settles, calm contrast after chaos, epic final hero frame. 🎬 Style Direction (Important) Ducati / BMW Motorrad / Top Gear cinematic aggression, Netflix automotive intensity, IMAX-scale realism, grounded physics, no cyberpunk, no neon, pure mechanical power + real-world adrenaline.

16:9
Seedance Creator Video 87
Verified prompt

15s / 180 BPM / ONE CONTINUOUS SHOT / 360 POV downhill stair run, viral energy, max chaos 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)."

15s / 180 BPM / ONE CONTINUOUS SHOT / 360 POV downhill stair run, viral energy, max chaos 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)."

16:9
K cinematic. Photorealistic no 3D render, no game engine, no game-cutscene
Verified prompt

Style: 8K cinematic. Photorealistic — no 3D render, no game engine, no game-cutscene aesthetic. Cinematography: naturalistic master cinematography with energy — reactive handheld-in-zero-G feel, dynamic reframing. Lighting: Natural light only — hard raw sunlight from one side, deep black-space shadow on the other, soft cool blue Earthshine and albedo glow from the pristine intact planet below. No fill. Color: 60:30:10 — dominant black space + white suit / secondary deep cobalt-blue Earth oceans & atmosphere / accent soft white cloud swirls + thin atmospheric limb. Camera: Physical cine lens. 180° shutter motion blur. Zero-G float with active micro-tremor and reactive sway. Skin/Fur: Pore and fur-level realism through the visor — fogged breath on glass, wet living canine eyes with catch-lights, real blinking, wet nose, fine facial whiskers, panting micro-movements. Acting: top-tier cinematic and REAL CANINE — natural blinking, darting eye-line, pupils reacting to flare, ear micro-flinches inside helmet, snout tension, lips parting on a panting breath, brow softening in pure awe, head gently tilting as the planet drifts past. Every motion reads as a real living dog, not an animation or mannequin. Physics: Inertia and zero-G respected — no down direction, no fake gravity. Composition: Rule of thirds + golden ratio, but allowed to break dynamically for impact. Single FREELY-DRIFTING suited canine figure against the immense, completely intact living Earth. Continuity: Dog, suit, and the perfect whole Earth identical across the take. Technical: 24fps smooth motion. 8K detail. No jitter. 8-second duration. WORLD — Below and filling the sky: the Earth completely intact, whole, and pristine — a perfect blue marble hanging in the void. No cracks, no fire, no lava, no explosions, no shattered fragments. Continents green and brown under soft white cloud systems, oceans deep cobalt, polar ice bright, the thin glowing atmospheric limb curving gracefully against black space. Real planetary mass and scale, rotating slowly with natural orbital motion. Soft Earthshine and sunlight underlighting the suit from below. Real orbital physics — not a game render. LOCATION — STYLE REFERENCE ONLY, not a fixed keyframe. Open vacuum in low orbit above a completely intact, living Earth — black starfield, the full unbroken planet filling the view, thin blue atmosphere glowing at the limb, soft cloud patterns and continents drifting slowly past. NO spacecraft, NO station, NO rocket in frame. Model extends the world; the dog floats free in open vacuum. ACTION — ONE CONTINUOUS TAKE, single unbroken move, NO cuts (8 seconds total). 0:00–0:02 (HOOK) — extreme tight on the dog's helmet visor as the brilliant blue limb of Earth curves across the glass right at the lens; the dog's warm brown eyes snap to it, blinking slowly and softening in pure awe inside the helmet. 0:02–0:05 — camera whips back and arcs around the dog with energy, revealing the intact canine suit and its freely-drifting untethered body, then craning out to expose the perfect whole Earth filling the sky, continents and cloud systems slowly rotating beneath. 0:05–0:08 — fast reactive push back toward the dog's face as sunlight flares across the visor; the dog turns its head gently to track the planet’s curve, eyes wide with wonder, panting breath softly fogging the glass bubble, floating small and alone against the vast living Earth as stars drift across the lens. CAMERA — DYNAMIC continuous move: reactive zero-G drift, energetic arcs and whip-reframes, quick push-ins and crane-outs, speed ramps within the single 8-second take (never a cut), micro-tremor and handheld-in-vacuum sway throughout. Camera reacts to the beauty — swings to follow the glowing atmospheric limb and sun-kissed cloud tops. Hard optical sun-flares and lens bloom whenever raw sun or the bright Earth limb crosses the front element. STYLE — Dominant black space + white suit 60% / Secondary deep cobalt-blue Earth 30% / Accent soft white clouds + atmospheric glow 10%. WB 5800K. Hard single-source sun, no fill, gentle cool Earthshine underlight from the intact planet. CONSTRAINTS — 21:9 aspect ratio. EXACTLY 8 SECONDS. ONE CONTINUOUS SHOT — absolutely NO hard cuts, even through speed ramps and whip-moves. Dynamic zero-G camera with reactive energy + micro-tremor. Default real-time, with occasional brief speed-ramp for impact (still one continuous shot, no slow-mo abuse). Dog is UNTETHERED — NO tether, NO cable, NO rope, attached to nothing, freely drifting. Suit stays fully INTACT — never breaks or tears. Intact Earth reads as real planetary mass with real atmosphere, oceans, clouds and orbital physics at colossal scale — NO destruction of any kind. Sun-flares optical. Wet canine eyes and snout behind visor with natural blinking and living micro-expressions; dog identity consistent across the entire take. Photoreal throughout. AUDIO — "NO MUSIC. SFX ONLY — diegetic and suit-internal audio. No score of any kind." Close suit interior: amplified calm dog panting with soft wonder, comms static hiss, suit fan hum, faint creak of the suit seams under reactive movement; external is pure silent vacuum with only the faintest muffled low-frequency orbital hum transmitted through contact.

Style: 8K cinematic. Photorealistic — no 3D render, no game engine, no game-cutscene aesthetic. Cinematography: naturalistic master cinematography with energy — reactive handheld-in-zero-G feel, dynamic reframing. Lighting: Natural light only — hard raw sunlight from one side, deep black-space shadow on the other, soft cool blue Earthshine and albedo glow from the pristine intact planet below. No fill. Color: 60:30:10 — dominant black space + white suit / secondary deep cobalt-blue Earth oceans & atmosphere / accent soft white cloud swirls + thin atmospheric limb. Camera: Physical cine lens. 180° shutter motion blur. Zero-G float with active micro-tremor and reactive sway. Skin/Fur: Pore and fur-level realism through the visor — fogged breath on glass, wet living canine eyes with catch-lights, real blinking, wet nose, fine facial whiskers, panting micro-movements. Acting: top-tier cinematic and REAL CANINE — natural blinking, darting eye-line, pupils reacting to flare, ear micro-flinches inside helmet, snout tension, lips parting on a panting breath, brow softening in pure awe, head gently tilting as the planet drifts past. Every motion reads as a real living dog, not an animation or mannequin. Physics: Inertia and zero-G respected — no down direction, no fake gravity. Composition: Rule of thirds + golden ratio, but allowed to break dynamically for impact. Single FREELY-DRIFTING suited canine figure against the immense, completely intact living Earth. Continuity: Dog, suit, and the perfect whole Earth identical across the take. Technical: 24fps smooth motion. 8K detail. No jitter. 8-second duration. WORLD — Below and filling the sky: the Earth completely intact, whole, and pristine — a perfect blue marble hanging in the void. No cracks, no fire, no lava, no explosions, no shattered fragments. Continents green and brown under soft white cloud systems, oceans deep cobalt, polar ice bright, the thin glowing atmospheric limb curving gracefully against black space. Real planetary mass and scale, rotating slowly with natural orbital motion. Soft Earthshine and sunlight underlighting the suit from below. Real orbital physics — not a game render. LOCATION — STYLE REFERENCE ONLY, not a fixed keyframe. Open vacuum in low orbit above a completely intact, living Earth — black starfield, the full unbroken planet filling the view, thin blue atmosphere glowing at the limb, soft cloud patterns and continents drifting slowly past. NO spacecraft, NO station, NO rocket in frame. Model extends the world; the dog floats free in open vacuum. ACTION — ONE CONTINUOUS TAKE, single unbroken move, NO cuts (8 seconds total). 0:00–0:02 (HOOK) — extreme tight on the dog's helmet visor as the brilliant blue limb of Earth curves across the glass right at the lens; the dog's warm brown eyes snap to it, blinking slowly and softening in pure awe inside the helmet. 0:02–0:05 — camera whips back and arcs around the dog with energy, revealing the intact canine suit and its freely-drifting untethered body, then craning out to expose the perfect whole Earth filling the sky, continents and cloud systems slowly rotating beneath. 0:05–0:08 — fast reactive push back toward the dog's face as sunlight flares across the visor; the dog turns its head gently to track the planet’s curve, eyes wide with wonder, panting breath softly fogging the glass bubble, floating small and alone against the vast living Earth as stars drift across the lens. CAMERA — DYNAMIC continuous move: reactive zero-G drift, energetic arcs and whip-reframes, quick push-ins and crane-outs, speed ramps within the single 8-second take (never a cut), micro-tremor and handheld-in-vacuum sway throughout. Camera reacts to the beauty — swings to follow the glowing atmospheric limb and sun-kissed cloud tops. Hard optical sun-flares and lens bloom whenever raw sun or the bright Earth limb crosses the front element. STYLE — Dominant black space + white suit 60% / Secondary deep cobalt-blue Earth 30% / Accent soft white clouds + atmospheric glow 10%. WB 5800K. Hard single-source sun, no fill, gentle cool Earthshine underlight from the intact planet. CONSTRAINTS — 21:9 aspect ratio. EXACTLY 8 SECONDS. ONE CONTINUOUS SHOT — absolutely NO hard cuts, even through speed ramps and whip-moves. Dynamic zero-G camera with reactive energy + micro-tremor. Default real-time, with occasional brief speed-ramp for impact (still one continuous shot, no slow-mo abuse). Dog is UNTETHERED — NO tether, NO cable, NO rope, attached to nothing, freely drifting. Suit stays fully INTACT — never breaks or tears. Intact Earth reads as real planetary mass with real atmosphere, oceans, clouds and orbital physics at colossal scale — NO destruction of any kind. Sun-flares optical. Wet canine eyes and snout behind visor with natural blinking and living micro-expressions; dog identity consistent across the entire take. Photoreal throughout. AUDIO — "NO MUSIC. SFX ONLY — diegetic and suit-internal audio. No score of any kind." Close suit interior: amplified calm dog panting with soft wonder, comms static hiss, suit fan hum, faint creak of the suit seams under reactive movement; external is pure silent vacuum with only the faintest muffled low-frequency orbital hum transmitted through contact.

7:3
SEGMENT 1 of 10 of one continuous music video. @Image1 is the performer
Verified prompt

SEGMENT 1 of 10 of one continuous music video. @Image1 is the performer — preserve her exact identity everywhere: cornrow braids flowing into long dark curls, silver chain-drop earring, thin gold pendant necklace, glossy lips. @Image2 is WARDROBE REFERENCE ONLY (ignore the mannequin head): black cropped boxy blazer, leopard-print skinny tie over black bodysuit, dark-blue denim ruffled micro mini skirt, gold chains, black loafers. @Audio1 is the master track — the only audio; no invented music or vocals. COMPOSITION RULE — CRITICAL: NO centered symmetrical frames. Every shot composes her on a lateral third (left or right of frame), uses negative space, foreground occlusion (railings, doorframes, parked cars, shoulders), leading lines of the street, over-shoulder angles, off-axis dutch tilts. The lens finds her, she never poses dead-center. PRECISE LIPSYNC — TOP PRIORITY, face sharp on every word: 0.0–2.0 "All— in!" / 3.0–4.0 "Lights up." / 5.0–6.5 "Deep breath." / 7.5–8.5 "Teeth out." / 10.0–10.5 "Yeah." / 10.5–15.0 "I don't do peace talks, I just do results — name…" Instrumental gaps: closed mouth. FILM CONTEXT: Act I cold open, LOCATION A — brownstone block, early golden morning, long shadows, burgundy 90s sedan planted down the street (returns in finale). Her 3 girls (Black women, Y2K street glam: baby tee + baggy denim, velour tracksuit, cropped puffer, bamboo hoops) wait below the stoop. Black girlie hustle vibe. Shot flow: 0–2s "All in!": shot from BEHIND the iron stoop railing — she bursts out the door framed in the right third through the bars; CRASH ZOOM IN keeping her off-center. 3–4s "Lights up": over-the-shoulder of one girl below — her face lands on the upper-left third. 5–6.5s "Deep breath": profile close-up hugging the left edge, the empty street filling the right two-thirds as negative space, she straightens the leopard tie. 7.5–8.5s "Teeth out": reflection framing — her face caught in a parked car's side window, off-axis. 10s "Yeah": whip to a low dutch wide from across the street — stoop and crew on the right diagonal, brownstone lines leading to her. 10.5–15s verse: she descends and walks the sidewalk hugging the frame's left third, camera tracking laterally with parked cars strobing the foreground; crash-zoom punch on "results" landing her mouth on a third, never center. Continuity: gold pendant visible; same crew whole film. Audio intent: @Audio1 only; faint morning city. Quality bar: expensive NYC rap film, editorial off-center cinematography, no AI gloss.

SEGMENT 1 of 10 of one continuous music video. @Image1 is the performer — preserve her exact identity everywhere: cornrow braids flowing into long dark curls, silver chain-drop earring, thin gold pendant necklace, glossy lips. @Image2 is WARDROBE REFERENCE ONLY (ignore the mannequin head): black cropped boxy blazer, leopard-print skinny tie over black bodysuit, dark-blue denim ruffled micro mini skirt, gold chains, black loafers. @Audio1 is the master track — the only audio; no invented music or vocals. COMPOSITION RULE — CRITICAL: NO centered symmetrical frames. Every shot composes her on a lateral third (left or right of frame), uses negative space, foreground occlusion (railings, doorframes, parked cars, shoulders), leading lines of the street, over-shoulder angles, off-axis dutch tilts. The lens finds her, she never poses dead-center. PRECISE LIPSYNC — TOP PRIORITY, face sharp on every word: 0.0–2.0 "All— in!" / 3.0–4.0 "Lights up." / 5.0–6.5 "Deep breath." / 7.5–8.5 "Teeth out." / 10.0–10.5 "Yeah." / 10.5–15.0 "I don't do peace talks, I just do results — name…" Instrumental gaps: closed mouth. FILM CONTEXT: Act I cold open, LOCATION A — brownstone block, early golden morning, long shadows, burgundy 90s sedan planted down the street (returns in finale). Her 3 girls (Black women, Y2K street glam: baby tee + baggy denim, velour tracksuit, cropped puffer, bamboo hoops) wait below the stoop. Black girlie hustle vibe. Shot flow: 0–2s "All in!": shot from BEHIND the iron stoop railing — she bursts out the door framed in the right third through the bars; CRASH ZOOM IN keeping her off-center. 3–4s "Lights up": over-the-shoulder of one girl below — her face lands on the upper-left third. 5–6.5s "Deep breath": profile close-up hugging the left edge, the empty street filling the right two-thirds as negative space, she straightens the leopard tie. 7.5–8.5s "Teeth out": reflection framing — her face caught in a parked car's side window, off-axis. 10s "Yeah": whip to a low dutch wide from across the street — stoop and crew on the right diagonal, brownstone lines leading to her. 10.5–15s verse: she descends and walks the sidewalk hugging the frame's left third, camera tracking laterally with parked cars strobing the foreground; crash-zoom punch on "results" landing her mouth on a third, never center. Continuity: gold pendant visible; same crew whole film. Audio intent: @Audio1 only; faint morning city. Quality bar: expensive NYC rap film, editorial off-center cinematography, no AI gloss.

16:9
A young Korean woman in her mid-20s with a naturally expressive face and a
Verified prompt

Main Subject A young Korean woman in her mid-20s with a naturally expressive face and a relaxed, approachable personality. She has medium-length dark chestnut hair loosely tied into a low ponytail with several strands escaping naturally around her cheeks and neck. Her skin has realistic texture with visible pores, faint acne scars on one cheek, tiny freckles near her nose, subtle under-eye shadows from waking up early, and naturally flushed cheeks from walking outside. She wears almost no makeup beyond light sunscreen and a touch of lip balm. Today's outfit reflects a comfortable weekend morning. She wears an oversized faded navy university sweatshirt with slightly stretched cuffs, loose beige cotton wide-leg trousers that wrinkle naturally while walking, clean white running shoes with light dirt marks around the soles, a simple silver watch on her left wrist, small silver hoop earrings, and a cream-colored canvas tote bag hanging over one shoulder. A folded reusable shopping bag peeks out from inside the tote. Throughout the entire video, maintain exactly the same facial identity, hairstyle, body proportions, clothing, accessories, and personality. Location A traditional neighborhood market in Busan on a calm Saturday morning around 9:15 AM. Unlike a tourist destination, this is a genuine local market serving nearby residents. Narrow covered walkways stretch between aging concrete buildings. Metal roofing allows thin shafts of sunlight to pass through small openings, creating moving patches of light across the floor. Fresh vegetables are neatly arranged in blue plastic crates. Handmade signs written in Korean hang above family-owned produce stalls. Buckets filled with green onions, garlic, chili peppers, mushrooms, and leafy vegetables line the aisles. Elderly vendors quietly greet familiar customers. Fresh seafood sits on crushed ice nearby, while small electric fans slowly rotate behind the counters. Plastic shopping baskets, folded cardboard boxes, old weighing scales, and stacked delivery crates contribute to the lived-in atmosphere. The concrete floor shows years of wear, with darker patches from recently mopped water and countless footsteps. The market feels warm, ordinary, and deeply authentic, with no polished displays, luxury branding, or tourist-oriented decorations. Visual Style Ultra-realistic documentary realism with an intimate slice-of-life atmosphere. Every action unfolds naturally without performance. The woman behaves exactly as someone running ordinary weekend errands would. She casually compares vegetables, smiles politely at vendors, pauses to think before choosing ingredients, and occasionally adjusts her tote bag while walking. Natural fluorescent lighting inside the market mixes with soft daylight entering from side streets, creating slightly uneven white balance typical of inexpensive early digital camcorders. Clothing wrinkles, fabric movement, facial expressions, and body language remain subtle and believable. Nothing appears staged or cinematic. Camera Style Entirely recorded using a consumer Sony Handycam MiniDV camcorder from approximately 2003–2005. The camera is operated casually by a close friend walking beside her. Handheld shake remains constant throughout. Framing frequently drifts too low or cuts off part of her head before the operator corrects it. Autofocus repeatedly shifts between foreground vegetables, hanging price signs, passing shoppers, and her face. Exposure pumps slightly whenever brighter outdoor entrances appear in the background. Zoom movements are hesitant and uneven. Slight rolling shutter distortion appears during quick pans. Soft contrast, faded colors, limited dynamic range, DV tape compression artifacts, mild chroma noise, slight sensor grain, and occasional dropped-frame judder reinforce the authentic home-video aesthetic. No stabilization. No cinematic tracking shots. No modern HDR. No color grading. Everything should feel accidentally beautiful rather than professionally filmed. 00:00–00:02 The recording begins while the camera is accidentally aimed toward rows of stacked cabbage and baskets of onions. After a brief moment, the operator quickly tilts upward, revealing the woman entering the market with her cream tote bag resting comfortably on her shoulder. She glances around with quiet curiosity before smiling to herself. Autofocus hunts between nearby vegetables and her face before finally settling. 00:02–00:04 She stops at a small vegetable stall run by an elderly woman arranging fresh spinach. She gently picks up two bundles, comparing them carefully while chatting politely in Korean. Her expressions remain relaxed and genuine. The camera slowly drifts toward neighboring stalls before awkwardly returning to her. 00:04–00:06 After choosing one bundle, she places it into her reusable shopping bag. The vendor weighs the vegetables using an older mechanical scale with a soft metallic click. She thanks the vendor with a respectful bow of her head. A passing shopper briefly blocks most of the frame, forcing autofocus to search again. 00:06–00:08 Continuing deeper into the market, she notices a stall displaying bright seasonal strawberries. She crouches naturally to inspect several baskets, lifting one slightly before smiling with quiet approval. Soft sunlight filters through gaps in the roof overhead, briefly illuminating her face while exposure adjusts slowly. 00:08–00:10 She purchases a basket of strawberries and carefully places it inside her tote bag. While organizing the groceries, one strawberry nearly rolls onto the floor. She laughs softly as she catches it just in time. The camera operator reacts a little late, missing the beginning of the moment before quickly reframing. 00:10–00:12 Walking toward the market exit, she pauses beside a small fishcake stand where steam rises gently into the cool morning air. She buys one warm fishcake on a wooden skewer. As she takes a careful bite, steam briefly fogs the lens while autofocus struggles between the rising vapor and her face. 00:12–00:15 She exits the covered market into bright morning sunlight carrying her groceries. The sudden change in lighting causes the camera to overexpose for several seconds before gradually correcting. She notices the camcorder, smiles warmly, raises the fishcake playfully toward the lens as if offering a taste, then laughs quietly before turning away. The camera follows for only a few more steps before dipping toward the pavement and cutting abruptly to black mid-motion. Audio Natural ambient sound only. Soft conversations between local shoppers. Plastic bags rustling. Rolling shopping carts. Vendors greeting customers. Mechanical weighing scale clicking. Footsteps echoing on worn concrete. Electric fans humming. Water dripping from recently washed vegetables. Distant scooter engines outside the market. Fishcake broth simmering softly. Light laughter. Canvas bags brushing against clothing. No background music. No narration. No cinematic sound design. Goal Create the feeling of discovering a forgotten family MiniDV tape from Busan in 2004, documenting nothing more than an ordinary Saturday grocery trip. The footage should feel deeply personal, imperfect, warm, and effortlessly authentic. Every interaction, camera mistake, lighting change, and environmental sound should convince the viewer they are watching a real home video rather than AI-generated footage.

Main Subject A young Korean woman in her mid-20s with a naturally expressive face and a relaxed, approachable personality. She has medium-length dark chestnut hair loosely tied into a low ponytail with several strands escaping naturally around her cheeks and neck. Her skin has realistic texture with visible pores, faint acne scars on one cheek, tiny freckles near her nose, subtle under-eye shadows from waking up early, and naturally flushed cheeks from walking outside. She wears almost no makeup beyond light sunscreen and a touch of lip balm. Today's outfit reflects a comfortable weekend morning. She wears an oversized faded navy university sweatshirt with slightly stretched cuffs, loose beige cotton wide-leg trousers that wrinkle naturally while walking, clean white running shoes with light dirt marks around the soles, a simple silver watch on her left wrist, small silver hoop earrings, and a cream-colored canvas tote bag hanging over one shoulder. A folded reusable shopping bag peeks out from inside the tote. Throughout the entire video, maintain exactly the same facial identity, hairstyle, body proportions, clothing, accessories, and personality. Location A traditional neighborhood market in Busan on a calm Saturday morning around 9:15 AM. Unlike a tourist destination, this is a genuine local market serving nearby residents. Narrow covered walkways stretch between aging concrete buildings. Metal roofing allows thin shafts of sunlight to pass through small openings, creating moving patches of light across the floor. Fresh vegetables are neatly arranged in blue plastic crates. Handmade signs written in Korean hang above family-owned produce stalls. Buckets filled with green onions, garlic, chili peppers, mushrooms, and leafy vegetables line the aisles. Elderly vendors quietly greet familiar customers. Fresh seafood sits on crushed ice nearby, while small electric fans slowly rotate behind the counters. Plastic shopping baskets, folded cardboard boxes, old weighing scales, and stacked delivery crates contribute to the lived-in atmosphere. The concrete floor shows years of wear, with darker patches from recently mopped water and countless footsteps. The market feels warm, ordinary, and deeply authentic, with no polished displays, luxury branding, or tourist-oriented decorations. Visual Style Ultra-realistic documentary realism with an intimate slice-of-life atmosphere. Every action unfolds naturally without performance. The woman behaves exactly as someone running ordinary weekend errands would. She casually compares vegetables, smiles politely at vendors, pauses to think before choosing ingredients, and occasionally adjusts her tote bag while walking. Natural fluorescent lighting inside the market mixes with soft daylight entering from side streets, creating slightly uneven white balance typical of inexpensive early digital camcorders. Clothing wrinkles, fabric movement, facial expressions, and body language remain subtle and believable. Nothing appears staged or cinematic. Camera Style Entirely recorded using a consumer Sony Handycam MiniDV camcorder from approximately 2003–2005. The camera is operated casually by a close friend walking beside her. Handheld shake remains constant throughout. Framing frequently drifts too low or cuts off part of her head before the operator corrects it. Autofocus repeatedly shifts between foreground vegetables, hanging price signs, passing shoppers, and her face. Exposure pumps slightly whenever brighter outdoor entrances appear in the background. Zoom movements are hesitant and uneven. Slight rolling shutter distortion appears during quick pans. Soft contrast, faded colors, limited dynamic range, DV tape compression artifacts, mild chroma noise, slight sensor grain, and occasional dropped-frame judder reinforce the authentic home-video aesthetic. No stabilization. No cinematic tracking shots. No modern HDR. No color grading. Everything should feel accidentally beautiful rather than professionally filmed. 00:00–00:02 The recording begins while the camera is accidentally aimed toward rows of stacked cabbage and baskets of onions. After a brief moment, the operator quickly tilts upward, revealing the woman entering the market with her cream tote bag resting comfortably on her shoulder. She glances around with quiet curiosity before smiling to herself. Autofocus hunts between nearby vegetables and her face before finally settling. 00:02–00:04 She stops at a small vegetable stall run by an elderly woman arranging fresh spinach. She gently picks up two bundles, comparing them carefully while chatting politely in Korean. Her expressions remain relaxed and genuine. The camera slowly drifts toward neighboring stalls before awkwardly returning to her. 00:04–00:06 After choosing one bundle, she places it into her reusable shopping bag. The vendor weighs the vegetables using an older mechanical scale with a soft metallic click. She thanks the vendor with a respectful bow of her head. A passing shopper briefly blocks most of the frame, forcing autofocus to search again. 00:06–00:08 Continuing deeper into the market, she notices a stall displaying bright seasonal strawberries. She crouches naturally to inspect several baskets, lifting one slightly before smiling with quiet approval. Soft sunlight filters through gaps in the roof overhead, briefly illuminating her face while exposure adjusts slowly. 00:08–00:10 She purchases a basket of strawberries and carefully places it inside her tote bag. While organizing the groceries, one strawberry nearly rolls onto the floor. She laughs softly as she catches it just in time. The camera operator reacts a little late, missing the beginning of the moment before quickly reframing. 00:10–00:12 Walking toward the market exit, she pauses beside a small fishcake stand where steam rises gently into the cool morning air. She buys one warm fishcake on a wooden skewer. As she takes a careful bite, steam briefly fogs the lens while autofocus struggles between the rising vapor and her face. 00:12–00:15 She exits the covered market into bright morning sunlight carrying her groceries. The sudden change in lighting causes the camera to overexpose for several seconds before gradually correcting. She notices the camcorder, smiles warmly, raises the fishcake playfully toward the lens as if offering a taste, then laughs quietly before turning away. The camera follows for only a few more steps before dipping toward the pavement and cutting abruptly to black mid-motion. Audio Natural ambient sound only. Soft conversations between local shoppers. Plastic bags rustling. Rolling shopping carts. Vendors greeting customers. Mechanical weighing scale clicking. Footsteps echoing on worn concrete. Electric fans humming. Water dripping from recently washed vegetables. Distant scooter engines outside the market. Fishcake broth simmering softly. Light laughter. Canvas bags brushing against clothing. No background music. No narration. No cinematic sound design. Goal Create the feeling of discovering a forgotten family MiniDV tape from Busan in 2004, documenting nothing more than an ordinary Saturday grocery trip. The footage should feel deeply personal, imperfect, warm, and effortlessly authentic. Every interaction, camera mistake, lighting change, and environmental sound should convince the viewer they are watching a real home video rather than AI-generated footage.

16:9
Anime visual reference sheet, Studio Ghibli art style, clean cream white
Verified prompt

Anime visual reference sheet, Studio Ghibli art style, clean cream white background. Bold clean outlines, cel shading, pure 2D anime illustration. FOOD: Raw dough ball dusted with flour. Stretched thin pizza base. Deep red San Marzano tomato sauce. Torn fresh mozzarella, bright white and wet. Fresh basil leaves, deep glossy green. Finished Neapolitan pizza with leopard char spots, bubbling golden mozzarella, a lifted slice with long cheese pull. TOOLS: Wooden pizza peel, round pizza wheel cutter, ladle, wood-fired oven interior glowing orange with open flame. COLOR PALETTE: Dough cream #F5ECD7, tomato red #C0392B, mozzarella white #F9F6F0, basil green #2D6A4F, char black #1A1A1A, crust gold #D4A55A, flame orange #FF6B35. Bold anime outlines, cel shading, Ghibli food illustration style, multiple reference panels clearly labeled.

Anime visual reference sheet, Studio Ghibli art style, clean cream white background. Bold clean outlines, cel shading, pure 2D anime illustration. FOOD: Raw dough ball dusted with flour. Stretched thin pizza base. Deep red San Marzano tomato sauce. Torn fresh mozzarella, bright white and wet. Fresh basil leaves, deep glossy green. Finished Neapolitan pizza with leopard char spots, bubbling golden mozzarella, a lifted slice with long cheese pull. TOOLS: Wooden pizza peel, round pizza wheel cutter, ladle, wood-fired oven interior glowing orange with open flame. COLOR PALETTE: Dough cream #F5ECD7, tomato red #C0392B, mozzarella white #F9F6F0, basil green #2D6A4F, char black #1A1A1A, crust gold #D4A55A, flame orange #FF6B35. Bold anime outlines, cel shading, Ghibli food illustration style, multiple reference panels clearly labeled.

135:152

Build Your Lyric Video Visuals

Create moving scenes, prepare reference images or explore prompts for your next visual idea.

Reference Images
Lyric Video Prompts

Seedance 2.5 Video Generation

Make short clips with Seedance 2.5

Create a short scene from text or a supported reference image. The generator shows the settings and credit cost available to your account before you submit.

Create with Seedance 2.5
Seedance 2.5 Video Generation
Seedance 2.5 video generation

How to Use Seedance 2.5

Make a clip in the generator by choosing an available mode, entering your input, and reviewing the settings shown before you submit.

1

Choose text to video or image to video

Pick the input mode offered in the generator. Use text to video to start from a written description, or image to video to animate a reference image if that mode is available for the selected model.

2

Enter a prompt

Describe the characters, scene, camera movement, actions, and visual style you want. The generator shows which inputs the selected model accepts.

3

Click generate

Check the credit quote shown before generation, then submit. Processing time and output quality vary, so review the result before using it.

4

Download

Open the finished clip in History, review it, and download the file you want to keep.

A Lyric Video Maker Workflow You Can Shape

Use the video and image tools to develop visual material for your project, then make the pacing and typography your own in the final edit.

Seedance 2.5 Model Notes

These notes cover what the generator currently shows for Seedance 2.5. Available inputs, settings, and capabilities depend on the model selected, so confirm them in the generator before you submit.

Text and image input

Create a short clip from a text prompt or a supported reference image. Select the input mode shown in the generator and review its settings before submitting.

  • Use Text to video turns a written description into a short clip. Results vary, so review the output.
  • Use image to video to animate a still image when the selected model supports image reference input.
  • Compare the generated clip with your reference image. Character consistency and fine detail are not guaranteed.
Create with Seedance 2.5

Optional Audio Settings

Audio options depend on the model. Check whether audio generation is offered for the selected model. If it is, review the settings and the credit quote shown before submitting.

  • The Audio in generated clips is not available for every model. Confirm what the selected model supports in the generator.
  • For music projects, download the visual clips and add your own music and timed lyric overlays in an external editor. RapLyrics does not synchronize lyrics automatically.
  • Combine generated clips with your own audio and lyric timing in your editing software.
Open the generator

Camera and Motion Direction

Guide your scenes with camera and motion direction, turning ideas into planned shots. Whether you need a close-up or a wide drone-style shot, the Seedance 2.5 video generator uses your written scene instructions; review the resulting camera movement.

  • Use camera movement guidance to plan pans, zooms, and tracking shots.
  • Add lifelike motion with realistic motion processing that follows the physics you describe.
  • The Seedance 2.5 video model lets you specify lighting, motion rhythm, and scene transitions in your prompt; check the generated clip against your brief.
Start Creating Video

Short Video Storytelling

Create short video concepts with Seedance 2.5. Review character details and scene continuity in each completed clip.

  • Review Seedance 2.5 character details and scene continuity in each completed clip.
  • Export clips for ads and social media campaigns.
  • Use text-to-video or image-to-video with the enabled Seedance 2.5 model. Only select the reference, output and audio options shown for it, and review the current credit quote before generating.
Create with Seedance 2.5

Why Use Seedance 2.5?

The Seedance 2.5 video generator can help with production bottlenecks. From audio options to scene control, check which features your selected model offers.

Reference Images

Describe a clear subject and one main action. In image-to-video mode, explain how the reference composition should move.

Audio Options

Check whether your selected Seedance 2.5 model offers synchronized sound, dialogue, sound effects, or background music. If available, review the audio in the finished clip. For music projects, download visual clips and add your own music and timed lyric overlays in an external editor.

Scene Control

You can describe camera movement, motion rhythm, lighting, scene style, and visual composition in your prompt. Check whether your selected model offers these controls, then compare the generated output with your creative brief.

Short Video Production

Use Seedance 2.5 for social media videos, ads, product demos, and short stories. Review the continuity of the resulting clips. Test multiple visual concepts and check whether your selected model supports video continuation.

Workflow Notes

“
Describe one subject, action and setting before generating. Keep the brief focused so the result is easier to review.

Seedance 2.5 FAQ

Quick answers about the Seedance 2.5 video model and what you can do in RapLyrics.

Seedance 2.5 is a video model available in the RapLyrics generator. Select it to make short clips from a text prompt or a supported reference image. Input options and settings are shown in the generator.

You can use a supported PNG or JPEG reference image with a clear subject. The generator shows which inputs are allowed for each enabled model.

Use a text prompt or a supported PNG or JPEG reference image. Check the inputs and settings shown for this model before generating. The current credit quote appears before you generate.

Check the output options shown in the generator. Audio output settings are separate from reference uploads. For music projects, download the visual clip and add your own music and timed lyrics in an external editor.

You can make short clips for social posts, product demos, and story scenes. Review each result and adjust the prompt or settings as needed.

Use a text prompt or a supported PNG or JPEG reference image. Check the inputs and settings shown for this model before generating. The current credit quote appears before you generate.

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.

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.

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@raplyrics.app with the task ID.

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@raplyrics.app with the task ID and details. A credit refund returns credits, not money to your payment method.

Email support@raplyrics.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.

Start Creating with Seedance 2.5

Compare the input modes and output settings in the selector. Current availability and credit costs are shown there.

Create with Seedance 2.5

raplyrics.app · Updated 2026-10-27

What's new on this page

  • 2026-10-27 — Added editable example prompts and separate drafts for text and reference modes, with an action to restore the example.
  • 2026-10-25 — Page content published.
RapLyrics

Turn lyrics into visual ideas and create AI video scenes for your next lyric video.

support@raplyrics.app ↗

Product

  • Create
  • Pricing
  • Blog
  • Developer API
  • MCP Server

AI Images

  • AI Image
  • Nano Banana Image Concepts
  • Flux Image Concepts
  • Grok Image Concepts

AI Videos

  • AI Video
  • Bottle Kick Challenge
  • Burger Thru Window
  • Kling Video Scenes
  • Seedance Video Scenes
  • Veo Video Scenes

Help

  • Contact

AI Resources

llms.txtFull guideOverviewFeaturesPricingFAQ
Ask AI about RapLyricsChatGPT ↗Claude ↗Perplexity ↗Gemini ↗Grok ↗
© 2026 RapLyrics. All rights reserved.
SitemapTerms of ServicePrivacy PolicyRefund Policy