AI Video Prompts for Retro & Vintage Video

Super 8 grain and light leaks, VHS scan lines and color bleed, faded Kodachrome warmth, and the analog imperfections that make a clip feel like it was pulled from an archive — these Seedance 2.0 retro prompts generate the visual time signatures of every era from the 1960s to the early 2000s.

Retro video is not nostalgia as decoration — it is a camera system specification. The mistake most retro AI video prompts make is treating vintage aesthetics as a mood instruction: "retro vibes" or "vintage feel" produces generic desaturated footage with a sepia overlay. What actually produces the visual language of a specific era is naming the recording format and its physical artifacts: the format is the aesthetic, and the aesthetic is the format. A Super 8 film clip from 1972 is identifiable not because someone described it as "vintage" but because of the specific grain structure of Kodak Ektachrome ASA 160, the light leak at the splice point, the slight warm color push from chemical development, and the 18fps frame rate that produces the stutter-motion that audiences have learned to read as "the past." Those specific physical properties are the direction, and naming them produces an era, not a vibe. Era-specific hardware specification is the single most powerful technique for retro video generation. Each recording format carries its complete artifact bundle as a unit — naming the format activates the full system simultaneously. Super 8 (1965–1980s) brings the dense, visually textured grain of reversal film stock, warm color science with lifted blacks and reduced contrast, the 18fps base frame rate that produces slightly accelerated-feeling motion in playback, and the characteristic soft focus at the edges of the frame from consumer lenses with limited resolving power. VHS (1980s–1990s) brings the horizontal scan-line structure, chromatic color bleeding at high-contrast edges where the luminance and chrominance channels separate, the tracking artifact horizontal band that drifts up the frame when the tape head alignment is marginal, and the over-boosted color saturation of NTSC composite video that makes skin tones orange and skies a slightly unnatural cyan. 16mm film (1950s–1990s) brings a larger grain structure than Super 8 with more definition, the silver-halide flicker between frames that produces a breathing quality in the exposure, and the possibility of the specific color palettes of different stocks — Kodachrome's warm reds and yellows, Fuji's cooler blues and greens, Ektachrome's high saturation that documents the hyper-reality of the 1960s–70s suburban aesthetic. Hi8 and early consumer digital (1990s–early 2000s) brings the digital-over-analog artifacts: the pixelated breakup at the edges of the recording window, the timestamp burned into the lower right corner (a single detail that immediately encodes the era), and the flat, slightly overlit look of CCD sensors without modern computational photography. Color science per era is the second layer, and it is separable from the hardware spec. The 1960s and early 1970s are Kodachrome's warm reds and oranges, lifted blacks, and the documentary aesthetic of available-light filmmaking — a world that looks slightly more saturated than reality, especially in yellows, reds, and the particular amber of incandescent interior light. The late 1970s into the 1980s push through VHS's NTSC composite color toward oversaturation of primaries, skin tones orange under fluorescent office lighting, and the blue-cast that early video cameras introduced in outdoor settings. The 1990s bring the era's specific flatness: early digital color science with compressed highlights, reduced shadow detail, and a cooler overall temperature than film. The early 2000s bring the green push of Canon and Sony prosumer camcorder color science, the HDR-before-HDR look of consumer cameras trying to hold both highlight and shadow detail and doing neither well. These are not filters — they are color systems, and naming them by era and source gives Seedance a palette instruction grounded in actual recording history. Physical artifacts are the third layer and the one that most clearly differentiates retro video generations from footage that merely looks old. Film grain is directional and organic — it moves differently than digital noise, clustering in the midtones and becoming less visible in the shadows and highlights. Naming the grain as "film grain, heavy in the midtones, reduced in the shadows" produces a more authentic result than "add grain." Light leaks occur at specific camera body weaknesses — the film door hinge, the lens mount — and they produce a warm orange or cool blue streak that enters from a consistent edge of the frame across a short clip. Scan lines in VHS are horizontal, fixed in frequency, and produce a visible raster pattern at high magnification. Color bleeding in VHS is directional — the chroma channel bleeds to the right of the luminance edge, producing a faint red or cyan echo shadow at every high-contrast boundary. Vignetting in Super 8 and early zoom lenses is strongest at wide-angle settings and at the aperture limits, producing a darker oval shadow around the edges of the frame that gradually brightens toward the center. Each of these is a named physical process, and naming it by its mechanism produces more accurate artifact generation than aesthetic descriptions like "old and grainy." The modern-retro or "analog" aesthetic is a fourth register that operates differently from period-accurate simulation. Modern creators using retro aesthetics in contemporary content (social media, music videos, brand content) are not trying to accurately reproduce a 1974 Super 8 clip — they are borrowing the visual language of that clip as a signal of authenticity, intimacy, and the particular warmth that analog imperfection communicates against the digital perfection of modern production. This is the aesthetic of lo-fi music video: a contemporary subject, a contemporary story, but filmed (or filtered) to look as though it was found in a shoebox. The camera instruction for modern-retro is: take a contemporary scene and apply the specific artifact grammar of one era's recording format without committing to era-accurate content in the subject matter. A 2024 subject in a contemporary setting, filmed with the specific grain and color science of 1978 Super 8, produces the modern-retro clip. The anachronism is the aesthetic — and naming both layers (the contemporary subject and the historical camera system) gives Seedance both halves of the instruction. The era of day grammar is the fifth element that anchors retro video in its historical moment without relying on costumes and props. Interior lighting in the 1970s meant incandescent tungsten warm throughout — no daylight correction, no LED flatness, the walls slightly yellow and the faces warm. Outdoor light in the 1960s through a 16mm lens with Kodachrome stock meant strong shadows with warm amber fill — not the cool overcast diffusion of modern commercial production. The color temperature of the ambient environment is often the fastest path to era recognition without any object-based period detail. A contemporary kitchen filmed with VHS color science under practical tungsten light reads as the 1980s regardless of whether the appliances are modern. Across all five techniques, the governing principle is the same as the realistic genre: retro is a camera system, not a content choice. The subject can be anything — a contemporary person, a modern city, an abstract motion — but if the recording format, color science, physical artifacts, and ambient light temperature are specified as a coherent era system, the viewer reads the clip as historical. Every prompt in this gallery applies that principle: the era is specified as a camera system, and the content is the subject. Copy a prompt, keep the format spec and artifact list, and swap in your subject and setting.

Seedance 2.0 AI video prompt: 【Style】
90s Hong Kong TV Drama Style, Vintage Film Grain, Warm Yellowish Tone, E

【Style】 90s Hong Kong TV Drama Style, Vintage Film Grain, Warm Yellowish Tone, Exaggerated Wide-Angle Lens Perspective, Extremely Hysterical Emotion, Chaotic, Noisy, Desperate. 【Scene】 Hong Kong Stock Exchange Hall in the 1990s, Floor Covered with Waste Paper, Electronic Screens in a Dismal Green (Plummeting Numbers). 【Character】 The Speculator: Wearing a 90s Wide-Shouldered Gray Suit, Disheveled Hair, Drenched in Sweat, Eyes Filled with Blood Vessels and Madness, Clutching a Brick Phone. 【Shot Breakdown】 [00:00-00:05] Shot 1: The Great Crash · Moment of Madness Frame: Close-up wide-angle shot. Protagonist standing in the center of the trading hall, surrounded by blurry running and screaming crowds. Action: Screaming into the Brick Phone, veins bulging, spittle flying. 【Dialogue/Subtitles】: "Don't be afraid! Technical Adjustment! Leverage me!" (Maximum Madness). Atmosphere: Background electronic display numbers jumping wildly, red and green lights intersecting, creating a suffocating sense of urgency. [00:05-00:10] Shot 2: A Moment · Rooftop Wind Frame: Quick editing (Jump Cut). Suddenly switching to the empty rooftop edge. Action: Back to the camera, suit jacket thrown aside, tie loosened. Wind blowing his hair and shirt. Clutching a crumpled stock certificate, body swaying. Atmosphere: Instantly transitioning from extreme noise to extreme Deafening Silence, only howling wind. [00:05-00:15] Shot 3: A Dream · Paper Snowfall Frame: Overhead shot. Action: Letting go, countless white stock papers falling like snow from the rooftop, scattering onto the prosperous yet cold Central Street. Close-up: Final frame on his desperate, hollow eyes (pupils losing highlight), a tear of regret crossing his face. 【Subtitle (Vintage Yellow Font)】: Stock Market Risks, Enter with Caution.

core_style: - 80s-90s Shaw Brothers movie style - early Hong Kong wuxia drama aesthetics - nostalgic Chinese wuxia film - vintage TV quality - warm and high-saturation color palette - retro film grain texture - slight Technicolor chromatic aberration - classic studio backdrop feel - soft stage lighting visual_quality: - 35mm film photography - physical film defects - vintage film texture - subtle chromatic aberration (dispersion) - soft focus effect - slight light flickering - strong bloom on highlight surfaces character_modeling: female_character: - classic 80s period drama makeup - dark eyeliner - peach-pink lip balm - exquisite braids with pink silk ribbons and flower accessories - traditional light blue and white Hanfu with floral embroidery and silk texture male_character: - classic wuxia young scholar appearance - long hair tied with a white silk ribbon reaching the waist - signature sideburns - clean-shaven face - pure white scholar/swordsman long robe (Zhiduo) script_and_storyboard: logic: sitcom editing logic with early physical transition effects scenes: - shot_1: "Close-up: A young woman looks affectionately at a black and white cow cat on a wooden table. Dialogue: 'If only you could turn into a handsome guy.'" - shot_2: "Medium shot: The cow cat is licking its paws, followed by a burst of retro white physical smoke effects in the center of the screen." - shot_3: "Transformation: The smoke dissipates, and a handsome man in a white robe appears where the cat was." - shot_4: "Over-the-shoulder shot: The woman looks pleasantly surprised and reaches out to touch the man's shoulder or chest. Dialogue: 'Wow, you really became a handsome guy!'" - shot_5: "Medium shot: The man has a serious expression, gesturing with an orchid finger while speaking enchantingly. Dialogue: 'Have you forgotten you already had me neutered? I've changed now, I'm your sister!'" - shot_6: "Close-up: The woman freezes with a shocked expression. Dialogue: 'Ah!?'" audio_and_post_production: - "Poof" transformation sound effect - nostalgic Hong Kong background music - AI voiceover with "Old Film" or "TVB dubbing style" accent

Seedance 2.0 AI video prompt: Main subject: young Korean woman, early 20s, natural everyday appearance, faded

Main subject: young Korean woman, early 20s, natural everyday appearance, faded charcoal-grey sleeveless crop top, loose high-waisted light-wash jeans, black canvas sneakers, black cord necklace, black wavy hair in a messy side ponytail with wispy bangs. Realistic skin texture, minimal makeup, warm and approachable personality. Maintain consistent identity, clothing, hairstyle, and appearance throughout the entire video. Location: Authentic Korean residential neighborhood during a calm late morning. Narrow concrete alleys, low-rise homes, small terraces, potted plants, laundry lines, bicycles, utility poles, overhead wires, mature trees casting moving shadows, quiet residential atmosphere. No stores, advertisements, cafés, crowds, or commercial activity. Visual Style: Ultra-realistic documentary realism. Genuine candid behavior. Natural body language. Unscripted slice-of-life feeling. Strong environmental authenticity. Rich real-world details and believable human motion. Camera Style: Early-2000s consumer DV camcorder aesthetic. Friend casually recording everyday moments. Heavy handheld shake, imperfect framing, frequent autofocus hunting, lens breathing, exposure pumping when moving between sun and shade, occasional motion blur, subtle rolling shutter, mild digital compression artifacts, faded colors, soft contrast, slight sensor noise. No stabilization. No cinematic camera moves. No modern color grading. 00:00–00:02 Outside a small house entrance. She sits on a low concrete wall adjusting her ponytail with both hands raised. A light breeze moves loose strands of hair. She smiles naturally while the camera struggles to hold focus. 00:02–00:04 The camera follows her into a narrow alley lined with potted plants and concrete walls. She notices a stray cat approaching and crouches down. Framing drifts off-center as the operator tries to keep up. 00:04–00:06 She gently pets and feeds the cat. Autofocus repeatedly shifts between her face and the animal. Morning sunlight flickers through leaves overhead. 00:06–00:08 Small front yard beside her house. She hangs laundry on a clothesline while fabrics sway in the breeze. Exposure changes as clouds briefly pass overhead. 00:08–00:10 On a quiet terrace with a ceramic coffee cup. She sits comfortably watching the neighborhood, occasionally brushing hair behind her ear. Loose handheld side angle with natural camera drift. 00:10–00:12 Close side profile. Someone off-camera greets her. She turns, raises her hand, smiles warmly, and casually says, “Annyeong.” The camera catches the moment slightly late. 00:12–00:15 Walking slowly down a tree-lined residential lane holding her coffee cup. She notices the camera, gives a small genuine smile, then looks away and continues walking. Recording cuts abruptly to black mid-motion as if the camcorder was switched off. Audio: Natural ambient sound only — morning birds, distant motorcycles, light wind, leaves rustling, faint neighborhood chatter, cat sounds, footsteps on concrete, fabric moving on clotheslines, subtle residential ambience. No music. No sound design. No narration. Goal: Authentic Korean neighborhood life captured like a forgotten home video from the early 2000s — candid, imperfect, realistic, warm, and deeply believable.

Seedance 2.0 AI video prompt: [CINEMATIC SETUP]
Film Style: 1994 high-budget action-crime aesthetic, 35mm film

[CINEMATIC SETUP] Film Style: 1994 high-budget action-crime aesthetic, 35mm film grain, rich cinematic texture. Lens: 24mm wide-angle anamorphic for a deep field of view during the long take; sharp focus. Color Grade: Contrast between cold fluorescent kitchen lighting (teals/whites) and warm, golden-hued opulent dining room lighting. Camera Behavior: Continuous one-shot long take (steadicam), aggressive whip-pans, and rhythmic push-in zooms on impacts. Audio Style: Immersive spatial sound; clashing silver trays, champagne corks popping like gunshots, high-tempo orchestral waltz music perfectly synchronized to the hits. [TIMELINE SECOND BY SECOND] 0-2s: [The Kitchen Start] The camera flies through swinging double doors into a chaotic kitchen. A chef uses a heavy silver tray to parry a punch, then slides a large fish across a counter to trip an attacker. [Physics] Flour and water spray realistically. 2-4s: [The Transition] The camera tracks backward rapidly through the corridor into the main dining hall. A combatant grabs a bottle of champagne, using the popping cork to blind an opponent before swinging the bottle. 4-7s: [Dining Hall Mayhem] Multitude fight in full swing. A waiter performs an acrobatic flip over a table, using two lobsters as makeshift pincers to grab an attacker's ears. [Camera] Violent, fast zooms into every punch and kick. 7-9s: [Rhythmic Action] The violence turns rhythmic, following the beat of an accelerated waltz. Hits land on the "downbeat." A thug is propelled backward through the air after a kick. 9-10s: [The Climax] A massive five-tier white wedding cake is in the center frame. The thug crashes spine-first into the center of the cake. [Physics] Frosting and sponge cake explode outward in slow-motion. The camera does a final, rapid zoom on his cream-covered face. [STYLE & QUALITY BOOSTERS] Ultra-realistic 8K textures, movie-level stunt coordination, tactile physics (shattering glass, splashing liquids), stable character features, high dynamic range, authentic 1990s formal wear textures, seamless motion blur.

Seedance 2.0 AI video prompt: Create a non-narrative VJ-style visual piece for a chaotic warehouse-rave / corr

Create a non-narrative VJ-style visual piece for a chaotic warehouse-rave / corrupted DnB track. Do NOT make it sleek, glossy, futuristic, polished, or cyberpunk. Avoid smooth sci-fi imagery, clean neon-tech aesthetics, luxurious club visuals, or shiny cinematic realism. The visual identity should feel raw, dirty, unstable, handmade, low-tech, analog-damaged, and collaged. The coolness should come from roughness, collision, grime, distortion, and visual accidents — not from futuristic cyber styling. Use a constantly shifting mix of: dirty warehouse rave fragments, underground club textures, CRT monitors, surveillance-camera imagery, VHS damage, scanlines, xerox-like graphics, photocopy textures, rave flyer collage, wet urban night fragments, industrial machinery, speakers, warning lights, cables, pipes, metal surfaces, elevator displays, body fragments, faceless silhouettes, crowd arms, typography, liquid distortion, smoke, fog, particles, overexposed light, hard shadows, signal loss, ghosting, frame tearing, mosaic collapse, rough graphic overlays, broken video feedback. Important: each generation should look different. Do not lock into one stable style, one stable palette, or one stable visual world. Random variation is essential. Some generations can feel more collage-like, some more surveillance-like, some more rave-documentary-like, some more abstract, some more graphic, some more degraded. Keep shifting. Overall visual references should feel closer to: bootleg rave visuals, underground club projections, damaged VHS mixtapes, pirate TV broadcasts, CRT feedback loops, photocopied rave flyers, late-night city fragments, industrial grime, chaotic mixed-media collage, rough editorial graphics, and broken analog video art. Structure: 1) Intro: sparse and ominous. Low information density. One unstable motif only — for example a CRT, warning light, body fragment, speaker cone, or typography fragment. Dark, minimal, pulsing. 2) Groove entry: begin layering environment, secondary motifs, overlays, and contamination. Slowly build complexity. 3) Main drop: aggressive multiplication. Let body fragments, industrial objects, typography, rave lights, urban fragments, CRT imagery, abstract textures, and damaged overlays collide. 4) Breakdown: not calm, but altered collapse. Darker, slower, more signal-damaged, more ghosted, more abstract, more degraded. 5) Final drop: maximum density. Everything fuses and spreads — collage, rave, body, city, CRT, typography, machinery, abstraction, and noise all layered into organized chaos. End with abrupt blackout, signal cut, white blast, or noise-out. Transformation rule: Do not merely stack elements. Make them infect each other. Faces become CRT noise. Typography melts into liquid. Neon becomes cables. Smoke becomes silhouettes. Speakers pulse like organs. Warning lights multiply like a crowd. Urban lights become graphic shapes. Industrial objects repeat like dancers. UI fragments should appear only as rough broken overlays, not sleek futuristic interfaces. Camera and editing should vary every generation: push-ins, pullbacks, scan-like movement, macro closeups, handheld instability, fisheye, overhead angles, pulsing zooms, abrupt freeze frames, split screens, repetition, strobing, sudden black frames, hard cut bursts, looping fragments, visual feedback. Tone: chaotic, eccentric, dirty, unstable, rough, aggressive, decadent, anti-polished, underground, confrontational, visually addictive. Avoid: sleek cyberpunk, smooth futuristic realism, glossy sci-fi, clean LED luxury, polished nightclub ads, tidy compositions, coherent worldbuilding, overly cinematic beauty, cheerful festival energy, elegant minimalism, stable style, or pretty commercial visuals.

Seedance 2.0 AI video prompt: 【Movie Style】: 90s Hong Kong Art Cinema style, vintage film feel, high ISO grain

【Movie Style】: 90s Hong Kong Art Cinema style, vintage film feel, high ISO grain, yellow-green tint, step-printing effect, melancholic atmosphere. 【Core Dialogue (for emotion control)】: "If memory were a can, I wish it would never expire." 【Video Duration】: 10 seconds 【Shot Script】: [00:00-00:04] Shot 1: Through the Glass. Scene: A red public phone booth filled with raindrops. Character: A person wearing a khaki trench coat, holding the receiver tightly, not speaking, just listening. Emotional Performance: Through glass refraction, their gaze appears hollow yet profound. Raindrops flow on the glass, distorting their face like an oil painting. Subtitle/Voiceover Feeling: The scene seems frozen, with only rain sounds. [00:04-00:07] Shot 2: Extreme Close-up & Micro-expression. Scene: Focused on the character's lips and half-face. Action: Whispering softly into the receiver. Lips slightly trembling, seeming to want to say something but holding back. Lighting: Bokeh from street neon lights flowing across their face, alternating between bright and dark. Dialogue Emotion Mapping: Expressing an extreme restraint and loneliness of "wanting to touch but pulling back". [00:07-00:10] Shot 3: Signature Smeary Slow Motion. Scene: Character hangs up the phone, turning to walk into the rainy crowd. Visual Effects: Using stop-motion feel, the character's back becomes blurry with motion blur, as if their soul remains in place while the body moves. Environment: Background of flowing city street lights, forming elongated light trails. 【Technical Parameters】: Handheld camera, shallow depth of field, color shift, emotionally intense.

Seedance 2.0 AI video prompt: Film stock: 35mm Kodak Vision3 500T, heavy organic film grain, high contrast.
Le

Film stock: 35mm Kodak Vision3 500T, heavy organic film grain, high contrast. Lens/Aperture: 35mm Anamorphic lens, f/2.8. Deep depth of field to see both characters clearly. Color Grade: "Saturated 90s Diner" palette. Warm nicotine yellows, bright red vinyl booths, and harsh fluorescent overheads. Camera Behavior: Slow, rhythmic "Shot/Reverse Shot" switching. Starting with a slow creeping zoom on the lead's face. Atmosphere: A half-empty, sun-drenched diner. Dust motes floating in the light. Tense, quiet, blue-collar grit. Audio: Immersive spatial sound design. The distant clinking of silverware, a coffee pot pouring. Dialogue lipsync: Character @ image1 leans in and says: "I'm gonna ask you one more time, and if you lie, God himself won't be able to find what's left of you." [IMAGE REFERENCES / LEGEND] @ image1: The lead enforcer. Maintain exact beard, dark sunglasses, and black headphones (worn around the neck for this scene). Keep exact same character, style, and lighting. Character 2: A skinny, sweating man in a cheap, rumpled grey suit sitting opposite him, trembling while holding a ceramic coffee mug. [TIMELINE SECOND BY SECOND] 0-4s: [Medium Shot - Over the Shoulder] + [Focus on Character @ image1] + [Action: He is calmly stirring a cup of black coffee with a silver spoon] + [SFX: Rhythmic metallic tink-tink-tink of the spoon against porcelain]. 4-8s: [Close-up] + [Dialogue lipsync: Character @ image1 stops stirring, looks up slowly, and delivers the line with a cold, terrifying calm] + [Physics: Small wisps of steam rising from the coffee cup]. 8-11s: [Reverse Shot] + [Focus on Character 2] + [Action: He visibly gulps, a bead of sweat rolling down his forehead, eyes darting nervously] + [SFX: Muffled sound of a waitress laughing in the far background]. 11-15s: [Low-angle Profile Shot] + [Character @ image1 slowly reaches into his pocket, pulling out a heavy, chrome-plated handgun and placing it quietly on the table next to his saucer] + [Lighting: Sunlight glints sharply off the chrome]. [STYLE & QUALITY BOOSTERS] Movie-level realistic facial features, no deformation, stable character consistency. Professional 90s crime film aesthetic. High-fidelity skin textures (pores, sweat).

Seedance 2.0 AI video prompt: Nostalgic 1986 American summer comedy, Fast Times at Ridgemont High aesthetic wi

Nostalgic 1986 American summer comedy, Fast Times at Ridgemont High aesthetic with golden-hour polish. A sun-drenched beachside diner at magic hour — red vinyl booths, chrome edges, a lazy ceiling fan, a Coca-Cola neon sign buzzing in the window. Two friends in their early twenties sit across from each other in a booth: Jessie in a red tee tied at the waist and denim cutoffs, long blonde hair in a loose ponytail; Mara in a fitted white t-shirt and faded Levi's, dark wavy hair. Between them sits a shared banana split with two spoons, towering whipped cream, one maraschino cherry on top. Outside the window, a red Corvette, the Pacific glinting gold behind it. [0s–4s] Medium shot of the booth, slow push-in. Jessie and Mara both eye the cherry at the top of the sundae. They glance at each other, then back at the cherry. A slow, knowing smile spreads across each face. Mara's hand drifts toward her spoon. [4s–8s] Whip-pan to a tight two-shot across the table. Both friends reach for the cherry at the same time — their spoons meet in the air with a bright ting. They freeze, eyes locked across the sundae. The ceiling fan spins lazily above them. A bead of melted ice cream rolls down the glass. [8s–12s] Cut to a low angle between their faces. They slowly lower their spoons, still staring each other down. Jessie raises one eyebrow. Mara raises one eyebrow back, higher. Jessie raises both. Mara raises both and adds a smirk. Jessie cracks first, bursts out laughing, throws her head back. Mara laughs too. [12s–15s] Wide pull-back. Mara, still laughing, casually picks up the cherry with her fingers and eats it in one bite. Jessie's laugh cuts off. Her jaw drops. Mara shrugs, grins directly at the camera. Freeze- frame on Jessie's shocked expression, Mara mid-grin. Warm 3600K golden-hour sunlight streaming through the windows as key, cool 5200K fluorescent fill, soft pink neon spill from the Coke sign, rim-lit blonde hair. 1986 Kodachrome palette — cherry reds, butter cream, denim blues, chrome silver. Anamorphic 2.39:1, shallow DOF, visible 35mm grain, subtle film-halation on highlights. Audio: Fender Rhodes groove underneath, a sax riff entering at 4 seconds, ambient diner sounds (sizzling grill, distant jukebox, quiet chatter), a bright metallic ting on the spoons meeting at 5 seconds, both friends' laughter at 10 seconds, a single vinyl record-scratch when Mara takes the cherry at 13 seconds. No dialogue. Maintain distinct identity: Jessie in red with blonde ponytail, Mara in white with dark wavy hair. No color or hair swaps. Preserve sundae geometry, stable booth layout. Avoid morphing between the two characters. --duration 15 --camerafixed false --ratio 21:9

Seedance 2.0 AI video prompt: Cinematic 1970s retro sci-fi adventure scene, 15 seconds, four shots, inside the

Cinematic 1970s retro sci-fi adventure scene, 15 seconds, four shots, inside the Captain’s classic retro futuristic spaceship cockpit, with curved white panels, glowing analog consoles, blinking colored lights, chunky switches, CRT screens, chrome details, warm practical lighting, and soft cinematic haze. Shot 1 (0–4s) Medium two-shot of the Captain flying the ship while Graeme sits beside him like a furry alien co-pilot, surrounded by glowing analog controls. The Captain speaks in a warm cheeky Australian accent, lightly scolding Graeme in an affectionate way. Dialog (Captain, Australian accent): “Now listen here, Graeme, just for once I’d like one trip where you don’t poke anything important.” SFX: soft cockpit hum, console beeps, gentle engine rumble, low alien grumble from Graeme Shot 2 (4–7s) Medium shot of Graeme reacting with expressive non-human noises and hand gestures, as if defending himself. The Captain glances sideways at him with a crooked grin. Dialog (Captain, Australian accent): “Yeah, yeah, that’s what you said last time.” SFX: alien warble, snort, chirrup, cockpit hum Shot 3 (7–10s) Medium two-shot as the Captain points lightly at Graeme while keeping one hand on the controls. Graeme settles and gives an understanding noise. Dialog (Captain, Australian accent): “You need to keep it together, mate.” SFX: soft acknowledging growl from Graeme, low hum, quiet console chatter Shot 4 (10–15s) A communications panel suddenly begins flashing red and a harsh emergency tone cuts through the cockpit. Both the Captain and Graeme turn sharply toward the console as the distress call comes in, the relaxed mood instantly broken. SFX: emergency alert tone, radio crackle, signal pulse, startled alien noise Cinematic 1970s retro sci-fi adventure, inside a glamorous villain base with glowing analog consoles, chrome pillars, web-like decorations, colored lights, smoke, and campy late-1970s sci-fi style. Shot 1 (0–4s) The pirate woman steps forward with a smug smile while the green alien spear women hold the Captain and Grave at bay. Dialog (Pirate Woman): “Take them to the examination room.” SFX: low base hum, spear energy hum, Grave grumble Shot 2 (4–7s) The spear women escort the Captain and Grave through the villain base. The Captain walks along under guard, trying to keep his cool. Dialog (Captain, Australian accent): “Examination room? Aw mate, that sounds deeply unnecessary.” SFX: footsteps, Grave warble, machinery hum Shot 3 (7–11s) The doors open to a bizarre retro examination chamber filled with glowing tubes, chrome restraints, blinking lights, and a strange theatrical machine in the center. Dialog (Captain, Australian accent): “Yeah nah… this is exactly the sort of room I try to avoid.” SFX: door hiss, electronic buzzing, Grave uneasy noise Shot 4 (11–15s) The Captain and Grave are chained or strapped into a fancy retro sci-fi restraint device, side by side, surrounded by glowing controls and weird scanning equipment. Grave makes nervous noises while the Captain looks around with dry disbelief. Dialog (Captain, Australian accent): “Grave, next time we ignore the distress call.” SFX: restraint clunks, machine hum, Grave worried grumble Cinematic 1970s retro sci-fi adventure, strange alien planet, the Captain and his furry alien companion Grave track a distress signal with a small silver scanner. The signal leads them to a hidden retro sci-fi base built into the rocks, glowing with strange lights, chrome details, and campy villain energy. As they approach, green alien warrior women with futuristic space spears suddenly surround them. Then the glamorous space pirate woman and the strange alien woman step out and reveal it was a trap. Classic late-1970s sci-fi movie look, practical set design, film grain, no music. Shot 1 (0–4s) The Captain and Grave follow the scanner across the alien landscape and spot the hidden base in the distance. Dialog (Captain, Australian accent): “Well, Grave… that’s either a distress beacon or the tackiest hideout in the galaxy.” SFX: scanner beeps, alien wind, Grave chirrup Shot 2 (4–7s) They move closer to the base, cautious. The Captain studies the place while Grave stays tight beside him. Dialog (Captain, Australian accent): “Stay close, mate. Places like this don’t exactly scream honest business.” SFX: footsteps, low ambient hum, Grave warble Shot 3 (7–11s) Green alien women with futuristic spears suddenly surround them from all sides. Grave startles and the Captain stops short, looking around at the ambush. Dialog (Captain, Australian accent): “Ah good, spears. Always the sign of a warm welcome.” SFX: sudden movement, spear hum, Grave growl Shot 4 (11–15s) The pirate woman and the strange alien woman step into view from the base entrance, smiling as if the trap worked perfectly. The Captain clocks the setup immediately. Dialog (Pirate Woman): “Captain… welcome.” Dialog (Captain, Australian accent): “Yeah, nah… starting to think this rescue mission was a bit of a stitch-up.” SFX: low villain hum, Grave grumble

Seedance 2.0 AI video prompt: 15 seconds, 16:9. The protagonist is from @image1 — lock her appearance complete

15 seconds, 16:9. The protagonist is from @image1 — lock her appearance completely. Face, skin tone, body, and outfit must remain consistent throughout. She wears a grey faded sleeveless crop top, baggy high-waisted light blue jeans, black canvas shoes, and a black rope necklace. Her black wavy curly hair is tied in a messy side ponytail with bangs. She is a Korean female with a distinct early 2000s vibe. The entire video is shot in a quiet Korean residential neighborhood — narrow concrete alleys, low houses with small terraces, front yards with clotheslines, potted plants, parked bicycles and motorbikes, large trees, and ubiquitous overhead power lines. No shops, no vendors, no commercial atmosphere. A real, lived-in community. The camera handling is key. It must look like a friend grabbed a DV camcorder and started recording — no plan, no setup, nothing. Strong handheld shake, constant re-framing, subject often drifting toward the edge of the frame, autofocus hunting, lens breathing, and unstable exposure. The footage should look faded, low-contrast, slightly washed out, with digital noise and compression artifacts typical of early 2000s home videos. No stabilization. No modern color grading. This aesthetic is non-negotiable. She starts by sitting on a concrete sidewalk fixing her ponytail, arms raised, showing a genuine smile as the wind blows her hair — the camera struggles to find focus. Next, the camera follows her into a narrow alley where she crouches to feed a stray cat that approaches her. Then, she is in a front yard hanging clothes on a laundry line, the morning breeze blowing everything, camera shaking and continuously focusing. In the middle segment, she sits on a front terrace holding a coffee cup, sitting quietly and looking toward the street — a loose, drifting shot from the side. This is followed by a close-up from the right side where she raises her arm, waving warmly to someone off-camera and saying "Annyeong" (Hello) — the camera captures the movement half a beat late. The final shot is a slow follow-shot down the street; she holds her coffee cup, notices the camera, turns slightly and gives a quiet smile — then the recording cuts abruptly to black mid-action, as if the camera was switched off. The audio must be strictly natural. Morning birds, breeze, distant motorbikes, faint neighborhood chatter, a cat meowing, the sound of a coffee cup, footsteps on concrete, and rustling leaves. No music, no sound design, do not add anything else.

Seedance 2.0 AI video prompt: Visual Core
Character Features: Consistently maintain features identical to [ima

Visual Core Character Features: Consistently maintain features identical to [image]. Including: exquisite facial contours, signature heavy pink blush, deep heterochromatic-looking pupils. Body proportions are curvaceous and well-proportioned. Hairstyle: Flaxen brown-green long hair identical to the image, presenting a naturally voluminous, slightly messy texture with a few stray strands blowing in the wind. Clothing: White ruffled pleated mini dress, equipped with striking light blue ribbon shoulder straps (tied in bows), the hem decorated with delicate small blue flowers. Wearing a thin gold necklace around the neck. Visual Style: Late 2000s personal Vlog aesthetic. Filmed using a raw handheld flip camera (such as Flip Video or early digital cameras). The footage is accompanied by intense random shaking, blurring from autofocus failure, slightly overexposed highlights, warm but faded low dynamic range colors, and fine digital noise. No modern filters or stabilization processing. Video Timeline 00:00–00:02 | Selfie at a Taiwanese wooden pier The camera focuses closely on the face for a selfie; she smiles brightly at the camera and speaks casually. Behind her is the shimmering sea and moored old wooden fishing boats. The blue ribbons on the white dress sway gently in the breeze. 00:02–00:04 | Walking through a Taiwanese coastal alley Tracking shot from behind; she is walking a stray dog through a narrow stone alley. The camera shakes violently due to walking, occasionally focusing on the walls. She glances back at the camera, her skirt swaying with her steps. 00:04–00:06 | Traditional Taiwanese small eatery Dim indoor lighting, increased digital noise. She sits side-by-side with an elderly stall owner, laughing while holding a cup of hot tea. The camera is slightly tilted, capturing the natural glow of the blush on her face under the warm light. 00:06–00:08 | Fishing pier under morning light She squats by the pier to feed a stray dog, the ruffles of her white mini dress spread across the wooden planks. Warm morning light shines from the side, creating noticeable lens flare; the colors are yellowish with slightly low saturation. 00:08–00:10 | Taiwanese village street Handheld shot. She walks while looking down at a small paper map in her hand, looking curious, occasionally looking up at the surrounding old red brick houses; sunlight passes through her hair, with details showing early digital sharpening. 00:10–00:12 | Overlooking the Taiwanese seaside Panoramic shot; she stands by the shore looking out at the sea, raising a hand to block the sun. The sea breeze is strong, blowing her flaxen long hair and the blue ribbons on her dress into a mess. Slight color shift occurs due to strong light. 00:12–00:15 | Pier ending Returning to the selfie perspective. She smiles and waves goodbye to the camera, says a few parting words, then reaches out to press the camera's power button; the screen ends abruptly during the blurry moment of the hand obstructing the lens. Audio Profile Pure ambient sound: The recording has obvious wind noise (the sound of wind blowing over the microphone). Details: Distant seagull cries, regular waves crashing on the shore, low hum of distant boat engines, stray dogs barking, blurred Hokkien/Chinese conversation inside the restaurant, footsteps on wooden floors. Vocals: Her voice sounds very close, with slight recording floor noise.

Seedance 2.0 AI video prompt: Single continuous shot, one take, no cuts, cinematic oner, photorealistic,
1990s

Single continuous shot, one take, no cuts, cinematic oner, photorealistic, 1990s horror film stock, heavy 35mm grain, slight gate flicker, desaturated cold palette, practical-effects realism, slow deliberate camera with subtle handheld breath, professional color grading, deep shadow, shallow depth of field, 180° shutter motion blur. SUBJECT: a young woman in a thin white nightgown, mid-twenties, barefoot, pale, dark hair loose, holding a single guttering candle in a brass holder, her hand cupped around the flame. Drawn, frightened, but moving forward. Same woman throughout, no drift. An old Victorian house at night, a long upstairs hallway lined with closed wooden doors, faded floral wallpaper peeling at the seams, a threadbare runner rug, dust hanging in the still air, one tall window at the far end spilling cold blue moonlight. COLOR 60:30:10 — 60% deep shadow black and cold blue moonlight / 30% warm amber candle glow pooling close around her / 10% accent of sickly green-grey in the peeling wallpaper and a faint red under one distant door. PHYSICS: the candle flame flickers and gutters with every movement and draft, shadows stretch and swing across the walls as the light shifts, the camera breathes with slow handheld weight, dust drifts in the candlelight, floorboards felt underfoot. 0–6s — THE APPROACH, real-time 24fps, very slow: the camera glides behind her at a crawl as she walks the long hallway, candle held high, the warm glow pushing back a sliver of dark while the cold blue end of the hall stays distant. Doors slide past on either side. Her breath is shallow. At the far end, one door stands slightly ajar, a thin sliver of red light leaking out. 6–7s — THE STOP: she halts before the ajar door. The candle flame bends flat sideways, as if something exhaled. Silence. Time begins to ramp. 7–12s — THE PRESENCE, slow motion 120fps: near standstill. The door drifts open another inch on its own. In the black gap, a pale gaunt face hangs at the wrong height, too tall, eyes hollow, mouth slack, perfectly still, watching her. Dust and a single drifting moth hang frozen in the candlelight. Her face in profile, lips parting, the flame reflected trembling in her wide eye. It does not move. That is the horror. 12–15s — THE SNUFF, snap back to 24fps: time cracks back, the candle blows out, the hall plunges to cold blue dark, and the woman spins and flees back down the corridor, the camera chasing in the gloom as doors slam shut one after another in a rolling wave behind her, the pale figure now standing full in the hallway where the candle was. AUDIO (no music): heavy oppressive silence, a distant ticking clock, floorboard creaks under her steps, her shallow breath. At the stop, dead air and a single low inhuman exhale that bends the flame. During slow-mo a muffled vacuum, only a faint high ringing and her trembling breath. At 12s the candle's snuff, then a rush of slamming doors and her bare feet pounding the runner as she flees. FORBIDDEN: no clean modern digital look, no oversaturated color, no jump-scare monster lunge, no fast strobing, no plastic CGI gloss, no smooth gimbal stabilization, no morphing or extra limbs on the woman, no glowing or neon eyes, no readable text or logos, no franchise or recognizable characters.

Seedance 2.0 AI video prompt: [CINEMATIC SETUP]
Anamorphic 35mm, fluorescent overhead practical lighting — the

[CINEMATIC SETUP] Anamorphic 35mm, fluorescent overhead practical lighting — the flat affectless light of a convention center or community hall, Kodachrome with muted institutional colors — beige carpet, folding tables, name badges, 1980s public television production aesthetic, ambient crowd murmur of an antique fair in the background, on-camera microphone audio quality [@IMG_1 LEGEND] @IMG_1 = the artifact: glossy grey latex-skinned figure with crimson spiked crown, ornate third eye medallion at forehead, wide blue-irised bulging eyes with copper pupils, oversized red lips open in frozen expression, pointed ears, jeweled collar, decorative metalwork throughout — displayed on a folding table under fluorescent light [SECOND-BY-SECOND TIMELINE] MODE: SINGLE TAKE 0–2s | locked medium on host and artifact | host — middle-aged, cardigan, reading glasses, name badge — holds a small reference card and speaks directly to camera in complete deadpan: "What we have here is a mid-period Threshold Vessel, probably 1200 to 1400 interdimensional, the craftsmanship on the crown detail is really exceptional" — artifact completely still | convention hall ambience, PA system murmur, host's flat measured voice 2–5s | locked medium | host sets down reference card, grips the artifact's face with both hands at the jaw and temples, and PEELS IT OFF in one clean motion — the face comes away like a rubber mask, clean at the edges — host holds it up briefly, examines it, sets it aside on the table | wet suction release sound, host's expression unchanged, murmur continues 5–8s | slow zoom out begins | the faceless artifact begins glowing at the eye sockets — deep amber light pulsing from inside — host still speaking: "The interior cavity confirms it's a functional vessel rather than decorative — you can see the original resonance chambers are still intact" — artifact's neck elongating slowly, extra joints forming | glow hum begins under convention ambience, wet organic stretching sound, host's voice unchanged 8–11s | zoom out continues, artifact now mid-transformation | artifact has grown two additional arms from the collar area, jeweled metalwork spreading across the table surface like roots, the spiked crown extending into the air above, third eye medallion now orbiting the head slowly — host tilts his reading glasses up, leans slightly to examine a detail: "The medallion drift is a little unusual, that could affect value, but overall condition is quite good" | host's voice steady and academic, transformation sounds layering — metal growth, organic expansion, amber light intensifying 11–14s | zoom out wide, full convention hall visible | artifact now filling the frame above the folding table — eight feet tall, arms spanning the aisle, surrounding antique fair patrons visible in background continuing to browse completely unbothered — host now looking up at it, nodding: "Comparable pieces went at auction last cycle for somewhere in the range of forty to sixty thousand interdimensional units, though the provenance documentation you've provided is a bit thin" | ambient fair noise unchanged, one patron in background briefly glances up then returns to browsing, transformation sounds now architectural — deep resonance 14–15s | wide locked | host removes his reading glasses, folds them, slides them into his cardigan pocket, looks at camera: "I'd get a second opinion before you sell" | artifact fully transformed behind him, pulsing, orbital elements still moving — host completely still and satisfied | ambient fair noise, single PA chime, cut [STYLE & QUALITY BOOSTERS + NEGATIVES] BOOSTERS: Host must read as completely genuine public television antique appraiser — no camp, no winking at the camera, the comedy is entirely in his absolute sincerity, convention hall background activity must continue normally throughout — no one reacting, folding table must stay in frame as anchor of normalcy throughout zoom, artifact transformation must escalate in scale and strangeness proportionally to host's increasing calm, fluorescent lighting must persist — no dramatic lighting shift onto artifact, VHS grain and flat TV color throughout NEGATIVES: No host reacting with fear or surprise at any point, no background crowd panicking, no dramatic music — convention hall ambience only, no artifact making sound directly — all transformation sounds are ambient and physical, no zoom moving faster than the transformation warrants

Seedance 2.0 AI video prompt: 经典的复古迪士尼动画风格。 场景一:在埃及宫殿里,我们跟随法老的年轻女儿穿过走廊奔向图书馆,却被挡在了门外,因为强大的胡狼神阿努比斯挡住了去路。阿努比斯双手叉腰

经典的复古迪士尼动画风格。 场景一:在埃及宫殿里,我们跟随法老的年轻女儿穿过走廊奔向图书馆,却被挡在了门外,因为强大的胡狼神阿努比斯挡住了去路。阿努比斯双手叉腰,腋下裸露在外。他表情严肃而漫不经心。 场景二:阿努比斯微微低头,问女儿要去哪里。 场景三:女儿没有回答,只是狡黠地一笑,然后掏出一根羽毛,伸向阿努比斯的右腋窝,这让阿努比斯有些摸不着头脑。 场景四:特写镜头展现了女儿的手轻轻地用羽毛在阿努比斯的腋窝上来回拂动,反复地重复着这个动作。我们听到背景中传来阿努比斯压抑的笑声,表明 he 非常怕痒。 场景5:阿努比斯上半身特写。阿努比斯咧嘴一笑,闭着眼睛发出闷闷的笑声,女儿继续用羽毛轻轻地在他腋下上下拂动。 场景6:阿努比斯试图保护自己,抬起手臂,却反而让腋窝更加暴露。女儿继续用羽毛轻轻地挠阿努比斯的腋窝,阿努比斯咯咯地笑个不停,双臂微微张开,完全没有试图遮掩腋窝。 场景7:女儿继续用羽毛挠阿努比斯的腋窝,阿努比斯咯咯地笑个不停,最后终于用双臂环抱住自己,保护腋窝,女儿这才停止挠痒。他还在咯咯地笑,最终妥协了,说她可以去图书馆,说完还忍不住笑了几声。 场景8:阿努比斯侧身让女儿开门进去。他漫不经心地叹了口气,说他真希望女儿不知道他有多怕痒。 阿努比斯肌肉发达,手臂上戴着金色的臂环。他的声音低沉。有人挠他的腋窝。 语音为英语。

Seedance 2.0 AI video prompt: Main Subject
Young Chinese woman, early 20s.
Natural appearance.
Black wavy hair

Main Subject Young Chinese woman, early 20s. Natural appearance. Black wavy hair loosely tied back. Slightly damp bangs. Light grey hoodie over a faded white tank top. Blue jeans. Black canvas sneakers. Consistent identity throughout. Location Small Chinese town during a light summer rain. Simple bus shelter. Wet pavement. Trees lining the road. Utility poles. Apartment buildings in the distance. Occasional scooters. Humid atmosphere. Puddles reflecting the sky. No commercial focus. Visual Style Ultra-realistic observational footage. Feels like a friend casually recording while waiting together. High image quality. Natural color reproduction. Realistic skin detail. Authentic rain behavior. No exaggerated vintage effects. No excessive degradation. No cinematic grading. The recording should feel genuine and unnoticed. Camera Treatment Good consumer digital camera from 2008–2012. Handheld but comfortable. Mostly stable framing. Small natural corrections. Occasional focus transitions. Minor exposure adjustments. Realistic motion. Clear facial detail. No heavy shake. No obvious artificial camera effects. The camera quietly documents the moment. 00:00–00:02 Standing beneath a bus shelter while light rain falls. She extends her hand beyond the roof to feel the rain. A few drops land on her sleeve. Small smile. 00:02–00:04 Sitting on the shelter bench watching the road. Rainwater drips from the shelter roof. She quietly observes passing traffic. Natural waiting behavior. 00:04–00:06 She checks the time on an old silver flip phone. The phone catches a soft reflection from the cloudy sky. She sighs slightly and puts it away. 00:06–00:08 A bus appears far down the road. She stands up instinctively. Hopeful expression. The camera follows naturally. 00:08–00:10 The bus passes without stopping. Water sprays lightly from puddles. She watches it disappear. Then laughs quietly at her own bad luck. 00:10–00:12 Rain grows slightly heavier. She adjusts her hoodie. A few wet strands of hair stick to her cheek. She sits back down. 00:12–00:15 Looking toward the road again. She notices the camera. A sheepish smile appears. She shakes her head lightly. Then looks back at the empty road waiting for the next bus. The camera stays on the scene for a moment before ending. Audio Light rain. Water dripping from the shelter. Distant scooters. Occasional traffic. Wet footsteps. Trees moving in the wind. Subtle town ambience. No music. No narration. No sound design. Generation Goal A completely ordinary rainy afternoon that feels remembered rather than filmed. Not a camera test. Not a cinematic scene. A small moment from someone's life that happened to be captured and later rediscovered.

Seedance 2.0 AI video prompt: [视觉风格与整体格调]
高强度的历史武术擂台场景,呈现20世纪初中国民国时期城镇广场的视觉美学;画面逼真,8K分辨率,采用低饱和度、深褐色调(Sepia)的复古

[视觉风格与整体格调] 高强度的历史武术擂台场景,呈现20世纪初中国民国时期城镇广场的视觉美学;画面逼真,8K分辨率,采用低饱和度、深褐色调(Sepia)的复古色彩风格;巨大的木制比武台周围环绕着身穿传统长衫的密集人群;低角度动态镜头跟随杂技般的格斗动作进行扫视拍摄。 • 0:00 - 0:01:广角全景。阴天之下,历史感浓厚的城市广场上聚集了大量人群,环绕着一座高耸的八角形木制武术擂台。 • 0:01 - 0:02:中景摇摄。一位神情严峻、身穿黑色传统汉服长袍的大师气势汹汹地站在擂台中央,向人群发出激烈的公开挑战。 • 0:02 - 0:03:惊喜登场。突然,一位年轻的东亚女性跃入画面——她身穿带有补丁的蓝色牛仔夹克、白色露脐上衣、牛仔短裤,脚蹬蓝色运动鞋,戴着蓝色棒球帽,并穿着印有柔和色调爱心图案的白色过膝长袜;她身侧挎着白色小包,姿态优雅地飞身跃上擂台。 • 0:03 - 0:04:近身交锋。大师猛冲上前发起凌厉攻势,但她动作流畅地闪避,两人在木质平台上展开了电光火石般的攻防格挡。 • 0:04 - 0:05:空中动作高潮。两名格斗者同时跃向空中;她使出一记高速伸展踢,正中对方胸口,迫使大师发出一声痛苦的闷哼,整个人向后倒飞出去。 • 0:05 - 0:07:平稳空中着陆。镜头下摇,她稳稳落回木板上,摆出平衡而帅气的姿态,神情泰然自若,头上的棒球帽也纹丝不动。 • 0:07 - 0:08:人群特写镜头。周围人群爆发出狂热的欢呼声,纷纷挥舞拳头,庆祝这精彩绝伦的一击。 • 0:08 - 0:10:对称构图特写。 镜头特写她的面部,突显出她戴着蓝色棒球帽帽檐下那既专注又沉稳的神情,正蓄势待发迎接下一位挑战者。 • 0:10 - 0:11:新对手登场。一双厚重的黑色皮革战术靴稳步踏上前景的木质擂台,低角度镜头将她与这双靴子一同纳入画面,展现出她直视下一位格斗对手时的姿态。 负面提示词 3D渲染、卡通、动漫、低分辨率

Seedance 2.0 AI video prompt: An 8-second cinematic game cutscene video. Retro 16-bit pixel-art Japanese side-

An 8-second cinematic game cutscene video. Retro 16-bit pixel-art Japanese side-scrolling game aesthetic with a low-poly 3D blocky character composited into the 2D pixel world. Modern Japanese sidewalk: pixel vending machines, utility pole, guardrail, distant buildings, blue sky. The protagonist is an extremely low-poly, solid dark-grey flat-colored blocky humanoid (cubic head, rectangular limbs, no facial features, no shading). HUD top-left: deformed cartoon intestine HP gauge (coiled small intestine flowing into large intestine, ending at anus icon). [0.0s - 1.5s] WALK & DODGE: Side-view camera. Blocky character walks right along the sidewalk, hunched, knees pressed together, urgent posture. A pixel-art salaryman NPC enters from the right; the character sharply sidesteps to dodge. HP gauge mostly white with faint pink tip. [1.5s - 2.0s] BICYCLE IMPACT: A pixel-art bicycle slams into the blocky character from screen left. Massive pixel impact starburst, debris flying, body buckles. Brief screen shake. [2.0s - 2.3s] TIME FREEZE: Sudden freeze. Color desaturates, audio drops to silence. [2.3s - 6.0s] BULLET-TIME ZOOM (centerpiece): Bayonetta-style bullet-time. Screen tints deep purple-violet, pixel clock- gear motifs rotate in background. Character suspended mid-air in contorted impact pose, floating in extreme slow motion. Camera zooms in as the intestine HP gauge enlarges from corner HUD to fill the entire screen behind the character. The gauge's white interior animates to red — fill flows visibly from the small intestine end, snaking through the coils, progressing through the large intestine curves, advancing toward the anus icon. Fill animation completes in approximately 3 seconds with a light snappy rhythm. [6.0s - 6.3s] FLASH: Red fill reaches the anus icon. Screen flashes white briefly. [6.3s - 8.0s] CLIMAX POSE: Background transforms into brilliant golden radiating burst with pixel sparkles. HP gauge fully red end-to-end, returned to top-left HUD. The blocky character snaps into an iconic dynamic dance pose: standing on one leg with the other knee lifted high, fedora-style hat brim tilted down over the cubic head, one arm thrust forward with finger pointed, hip cocked sharply. Pose held. Camera locked. Sparkles continue radiating. === STYLE & TECHNICAL === - Consistent retro 16-bit pixel-art environment throughout - Low-poly 3D blocky character preserved in every shot - Intestine HP gauge design preserved (coiled tubes with anus icon) - Side-scroll camera shots 1-2, dramatic zoom shot 3,

Seedance 2.0 AI video prompt: [Core Concept]

“A real person naturally existing inside a pixel RPG game world”

[Core Concept] “A real person naturally existing inside a pixel RPG game world” 👉 Background = Pixel art 👉 Character = Photorealistic (identical to the real person) 👉 Key = No sense of mismatch [🚨 Absolute Rules – Top Priority] Must be exactly the same person as in the uploaded image Do NOT alter facial structure, eyes, nose, mouth, or proportions Maintain original hairstyle Preserve natural skin texture Do NOT transform into a different-looking person 👉 “Composited look ❌ / Naturally co-existing in the same space ⭕” [❗ Scale Adjustment Rule – Critical] 👉 Must be applied Character size must be 25–35% of the total frame height or less Maintain the same scale ratio as NPCs/background people Must feel naturally comparable to nearby objects (benches, streetlights, shops) 👉 Forbidden: Filling the center of the screen ❌ Large, model-like portrait scale ❌ 👉 Core idea: “A playable character size within a game world” [Distance & Lens Settings] Camera distance: Mid-range (full body visible + enough environment) Lens: 28mm–35mm (natural perspective with environmental depth) 👉 Effect: Character appears smaller, environment becomes more prominent [Character Placement] Positioned slightly below center Clearly grounded (no floating) Must include shadows consistent with lighting direction [Character Style] Fully photorealistic (NO pixelation) Original outfit must be preserved Natural NPC-like presence (front-facing or slight angle) [Background – Pixel World] High-quality pixel art (16-bit / 32-bit) based on {{CITY}} 👉 Landmark examples (Osaka): Dotonbori Glico sign Tsutenkaku Tower Riverside walkway Takoyaki shops 👉 Must be instantly recognizable as {{CITY}} [Spatial Composition] Foreground: streets, benches, shops Midground: character (small scale) Background: cityscape + landmarks 👉 Strong sense of depth is required [Game UI Elements] Top-left: pixel-style character profile Top-right: mini-map Right side: quest panel Example: “Explore {{CITY}}” “Go to Dotonbori (0/1)” Bottom: joystick + inventory + camera button [Mood & Direction] Daytime / clear weather Warm color tones Emotional RPG atmosphere [Quality Contrast] Background: high-density pixel art Character: ultra high-resolution photorealism Aspect ratio: 9: 16 (mobile game format) 👉 Core contrast: “Pixel world + real human” [Final One-Line Summary] A high-quality pixel-art RPG world set in {{CITY}}, featuring a photorealistic person scaled correctly as a small in-world character (25–35% of frame height), naturally integrated into the environment with proper perspective and shadows, including game UI elements, cinematic composition, ultra-detailed, 4K resolution.

Seedance 2.0 AI video prompt: [0:00–0:02] Title Card: Clean minimal text animation: DESERT REVERIE fades in ce

[0:00–0:02] Title Card: Clean minimal text animation: DESERT REVERIE fades in centered, thin serif white font, subtle letter spacing expand animation, over a blurred desert background (soft bokeh of red mesas and blue sky). Text holds for 1.5s then fades out smoothly. [0:02–0:05] Establishing Shot: Wide static shot, Monument Valley desert at midday. A vintage teal 1960s muscle car sits parked on a dirt road, red sandstone mesas in the background, clear blue sky. A man in a fringed jacket and cowboy boots reclines on the hood, hands behind his head, completely relaxed. Heat haze shimmers faintly above the ground. [0:05–0:09] Rising Action: Low angle GoPro shot from near the front bumper, slowly tilting upward. A powerful brown horse leaps into frame from the left, mid air, legs tucked, mane and tail whipping with motion. Camera holds steady as the horse arcs gracefully over the car and the reclining man, muscles rippling naturally, correct anatomy maintained (four legs, proper joint bends, no warping). [0:09–0:13] Landing & Dust: Camera transitions to a slow dolly in from the front of the car. Horse lands just behind the vehicle, front hooves touching down first, kicking up a dramatic cascade of dust and sand in realistic particle simulation. Man on the hood remains still and unfazed, jacket fringe fluttering slightly in the wind. Golden desert light, hard natural shadows. [0:13–0:15] Final Hold: Slow motion ramp (0.5x) on the settling dust cloud, mesas sharp in the background, sky calm and clear. Gentle fade to black. Technical requirements: Horse: exactly 4 legs, correct joint articulation, no limb warping, no extra hooves. Man: correct hand/finger anatomy (5 fingers each), no facial morphing. Car body lines and wheels remain stable, no distortion. Consistent dust/sand particle physics, no flicker artifacts. No watermarks, logos, or text overlays except the title card. 16:9 aspect ratio throughout, no letterboxing Color grading: warm desert tones, teal car accent, natural sky gradient, cinematic contrast.

Seedance 2.0 AI video prompt: Completely remake the video to be in a PS1 style.  IMG_1 is a replacement frame

Completely remake the video to be in a PS1 style. IMG_1 is a replacement frame showing the kind of style desired. IMG_2 is a redone version of the hallway scene. Apply this look to all other shots. Person on the TV screen is a low poly figure. Transform the entire video into an authentic screenshot captured directly from a late-1990s PlayStation 1 (PS1) video game running on original hardware. Re-render every single element of the scene — every object, character, surface, background, lighting, and detail — as low-polygon 3D models with clearly visible triangular facets, flat angular geometry, and no smoothing or subdivision whatsoever. Use extremely low-resolution textures (256×256 pixels or smaller) that are blurry, pixelated, and heavily compressed, with obvious tiling seams, mipmapping artifacts, and poor UV mapping. Apply classic PS1 affine texture mapping across all surfaces so textures visibly stretch, warp, wobble, and distort unnaturally with any change in perspective or camera angle (especially noticeable on floors, walls, and curved objects). Remove all anti-aliasing entirely — every edge must be sharply jagged and aliased with prominent stair-stepping. Use only basic flat shading or simple Gouraud vertex shading with no dynamic lights, no real-time shadows, no specular highlights, and no advanced effects. Simulate the PS1’s 16-bit color depth and 5-5-5 RGB limitations by introducing visible checkerboard or ordered dithering patterns in all color gradients, skies, shadows, and semi-transparent areas to prevent banding. Include typical PS1 graphical quirks: subtle vertex snapping/jitter/wobbling on moving or angled geometry, minor polygon pop-in or Z-fighting where appropriate, and a limited draw distance that may softly fade into a low-detail fog. The overall resolution should feel like a raw 320×240 or 640×480 PS1 framebuffer output, giving the whole image a slightly soft yet crunchy retro pixel look when viewed at modern sizes. Preserve the original scene composition and camera angle exactly, but convert everything into this pure PS1 3D style as if the photo itself were modeled and rendered inside an actual PS1 game. No text overlays, no HUD elements, no subtitles, no menu graphics, no scanlines, no CRT curvature, and no modern post-processing of any kind — just a clean, direct screenshot from the console’s video output.

Seedance 2.0 AI video prompt: Main subject: Young Korean couple, both early-to-mid 20s, fresh-faced and natura

Main subject: Young Korean couple, both early-to-mid 20s, fresh-faced and naturally attractive. Woman: long dark hair in a loose low bun with strands falling out, wearing an oversized soft beige hoodie and black bike shorts, glowing skin. Man: short textured black hair, wearing a white sleeveless tank and grey sweatpants, gentle and playful vibe. Keep their looks, outfits, and loving chemistry perfectly consistent across shots. Location: Charming Seoul suburban residential area at golden sunrise. Winding alleyways between colorful low-rise apartments, rooftop gardens with flowers, small balconies with drying clothes, steam from breakfast drifting out windows, birds on power lines, warm sunlight painting everything in soft orange and pink hues. Visual Style: Bright, heartwarming lifestyle realism with a dreamy morning glow. Soft bokeh in backgrounds, gentle lens flares from rising sun, vibrant yet natural colors, cozy and aspirational feel that makes viewers smile and feel warm inside. Focus on tender couple connection, small joyful gestures, and the beauty of simple shared moments. Camera Style: Mid-2010s smartphone video aesthetic (like an old iPhone 6 or Galaxy S5 recording). Casual vertical or slightly tilted handheld footage from one of them holding the phone. Light digital stabilization with occasional jitters, smooth but imperfect panning, auto white-balance shifts, subtle lens flare from morning sun, minor compression artifacts, natural color grading with slightly boosted warmth, occasional finger in frame or thumb occlusion at edges. No professional moves, feels like personal couple vlog footage. 00:00–00:02 Close-up of them waking up together on a small bed by the window. She sleepily smiles and pulls him in for a morning kiss on the forehead. Golden sunrise light pours in. 00:02–00:04 In their tiny kitchen, he makes coffee while she hugs him from behind, resting her chin on his shoulder. They sway together laughing as the coffee brews. 00:04–00:06 Stepping out to their small balcony. They feed leftover rice to birds on the railing. She points excitedly at a bird; he wraps his arms around her from behind. 00:06–00:08 Walking hand-in-hand down the sunny alley. They stop to take a quick selfie together, making silly faces then a sweet kiss on the cheek. 00:08–00:10 Sitting on a low wall sharing one pair of wired earphones, listening to music. She rests her head on his shoulder, both gently nodding to the beat with peaceful smiles. 00:10–00:12 Playful moment — he pretends to run away with her coffee cup; she chases him a few steps, both laughing brightly in the morning light. 00:12–00:15 Back at their door. They turn to the camera together, wave cutely, blow a kiss, and say “Have a good day!” in Korean with big smiles. Screen fades warmly as they step inside. Audio: Gentle natural morning ambience (soft birds, distant city wake-up sounds, light wind) mixed with faint, cheerful lo-fi beat playing from their shared earphones. Subtle fabric rustles, footsteps, happy laughter, and warm couple whispers. Cozy and uplifting without overpowering. Goal: Create an irresistibly heartwarming, relatable “couple goals” morning routine that feels genuine and aspirational — perfect for evoking smiles, relationship envy, and high shareability. Designed to go viral as feel-good everyday romance content.

Seedance 2.0 AI video prompt: use [@ image ]Cinematic 16:9 ultra-wide editorial bathroom scene, realistic live

use [@ image ]Cinematic 16:9 ultra-wide editorial bathroom scene, realistic live-action photography style. A narrow retro tiled bathroom with beige, tan, and slightly greenish mosaic walls, black tiled floor with white grout lines, white ceramic toilet at the end, toilet paper holder on the right wall, muted beige curtain behind the toilet. High-contrast artificial lighting, saturated mixed warm and cool tones, visible film grain, slight vignette, rounded vintage photo-frame corners. [0–2s] Camera starts outside the narrow bathroom door, handheld wide-angle lens, slightly tilted perspective. The bathroom is empty at first. The white toilet is centered at the end of the narrow tiled room. Subtle flickering bathroom light, gritty retro snapshot mood. [2–4s] The woman enters the bathroom with confident messy morning energy. She has dark hair with multiple cylindrical hair rollers in dark and purple tones, oversized white sunglasses with dark lenses, loose oversized off-shoulder white t-shirt, metallic open-toe sandals, and holds a dark cylindrical bottle in one hand. Camera slowly dollies backward as she walks in, exaggerating the narrow tiled walls with wide-angle distortion. [4–6s] She stops in front of the toilet, turns around naturally, then casually reaches down and lowers her light blue shorts/underwear to the upper thighs in a non-explicit, modestly framed way. Her oversized loose white t-shirt covers the body clearly. Camera stays at a tasteful medium-wide angle, focused on the action and attitude, not sexualized. No nudity visible. [6–8s] She backs up toward the white ceramic toilet and sits down with a relaxed, comedic morning-after attitude. The camera dips slightly lower, emphasizing the black tiled floor, metallic sandals, and strong perspective lines. Her feet land flat on the tiles, legs apart naturally, with the lowered clothing visible only around the upper thighs. [8–10s] She leans forward, rests one arm across her lap, then raises the dark bottle toward her lips. The toilet paper holder remains visible on the right wall. Her oversized white sunglasses and hair rollers dominate the frame, giving a bold retro fashion editorial look. [10–12s] Smooth push-in from wide shot to medium close-up as she drinks from the bottle. High-contrast skin highlights, reflective sunglasses, gritty film grain, saturated mixed warm and cool tones. End with a stylish freeze-frame feeling like a vintage fashion photo. Camera style: wide-angle lens, low perspective, handheld micro-shake, slow dolly-in, realistic movement, smooth cinematic transition, strong leading lines from bathroom tiles, retro editorial photography. Mood: messy glamorous morning-after vibe, bold fashion editorial, awkward comedy, stylish but realistic, non-explicit, no sexual framing. Negative prompt: nudity, exposed genitals, explicit sexual content, fetish framing, erotic pose, see-through clothing, extreme close-up of private areas, unrealistic body, distorted hands, extra limbs, broken face, bad anatomy, cartoon, CGI, plastic skin, over-smooth skin, warped toilet, messy tiles, flickering face, inconsistent sunglasses, inconsistent hair rollers.

Seedance 2.0 AI video prompt: Main Subject: Young Korean woman, early 20s. Natural appearance. Black wavy hair

Main Subject: Young Korean woman, early 20s. Natural appearance. Black wavy hair loosely tied into a slightly messy ponytail with wispy bangs. Light grey zip hoodie worn open over a faded white tank top. Relaxed blue jeans. Black canvas sneakers. Natural skin texture, minimal makeup, ordinary everyday look. Consistent appearance throughout the video. Location: Authentic Korean residential neighborhood during a light summer rain shower. Narrow concrete alleys, low-rise houses, small gardens, potted plants, bicycles, utility poles, overhead cables, wet pavement, puddles, rain-darkened walls, leafy trees. Camera Style Early-2000s consumer DV camcorder. Friend casually filming. Heavy handheld shake. Imperfect framing. Subject frequently drifts toward frame edges. Late reframing. Autofocus hunting. Lens breathing. Exposure pumping. Motion blur. Rolling shutter. Digital compression artifacts. Slight sensor noise. Soft detail. Faded colors. Low contrast. Occasional blown highlights. No stabilization. No cinematic movements. No modern color grading. The camera operator behaves like a real friend with no filmmaking experience. 00:00–00:02 Standing beneath a small apartment awning while rain falls across the street. She leans forward and extends her hand into the rain to test how heavy it is. A passing vehicle somewhere off-frame splashes water nearby. She immediately laughs and pulls her hand back. The camera misses part of the reaction because the operator reframes too slowly. Rain droplets briefly appear on the lens. Autofocus hunts between her face and the rainy street. 00:02–00:04 She steps into the drizzle and starts walking down the narrow alley. The camera follows unevenly from behind. Her sneakers splash through shallow puddles. Wet strands of hair begin sticking to her cheek and neck. Wind moves her hoodie slightly. The operator almost loses her from frame while turning a corner. 00:04–00:06 Passing a row of potted plants outside a house. She casually brushes rainwater from a large leaf. The camera unexpectedly focuses on the leaf instead of her face. Exposure shifts as the scene moves from open sky into tree shade. She continues walking before camera catches up. 00:06–00:08 A neighborhood cat shelters beneath a parked bicycle. She crouches down briefly and says a few friendly words. The cat sniffs her hand. Camera focus repeatedly jumps between the bicycle wheel, the cat, and her face. One moment is partially blocked by the operator's movement. 00:08–00:10 Walking again. Rainwater drips from overhead branches onto her shoulder. She reacts naturally and laughs to herself. The camera is slightly too close and awkwardly reframes. A gust of wind moves nearby leaves and loose hair strands. 00:10–00:12 Near a small intersection. She pauses while waiting for a scooter to pass in the distance. The camera drifts toward the wet road before finding her again. She wipes rain from her forehead using her sleeve. Her clothing shows subtle dampness from the weather. 00:12–00:15 Walking away down the rain-darkened street. The camera trails several steps behind. She suddenly realizes she is still being filmed. She glances back over her shoulder. A small genuine smile appears. She looks away again and keeps walking. The operator lowers the camcorder slightly. Recording abruptly cuts to black mid-motion as if the camera was accidentally switched off. Audio (Natural only) Light rainfall. Water dripping from roofs and leaves. Footsteps on wet concrete. Distant neighborhood traffic. Occasional scooter passing far away. Birds sheltering in trees. Rustling leaves. Faint residential chatter. Cat sounds. Subtle wind. No music. No narration. No sound design. No added effects. Generation Priority Authenticity > Beauty Believability > Cinematics Natural Imperfections > Technical Perfection The final result should look indistinguishable from a real early-2000s camcorder scene.

Seedance 2.0 AI video prompt: 45秒垂直短劇,9:16,電影感,8世紀日本奈良時代古風,1950年代日本舊膠片電影質感。

場景: 奈良時代的幽靜山間湖泊,清晨薄霧繚繞,古松參天,湖水清澈,

45秒垂直短劇,9:16,電影感,8世紀日本奈良時代古風,1950年代日本舊膠片電影質感。 場景: 奈良時代的幽靜山間湖泊,清晨薄霧繚繞,古松參天,湖水清澈,充滿古代日本自然與神祕氛圍。 角色: 漁夫伯良(Hakuryo):28歲,英俊健壯的日本男子,高挺鼻樑、劍眉星目、深邃黑眸、輪廓分明的下顎線,皮膚古銅色,肌肉結實健壯。黑髮束成奈良時代男子髻,穿著深褐色麻布短上衣、麻布褲,赤足。 天女:絕美出塵的仙女,細長鳳眼、櫻桃小口、雪白肌膚、精緻小V臉。長黑直髮及腰,僅以白玉簪簡單挽起部分。在湖中與剛上岸時穿著露肩粉紅色奈良時代傳統內襯,典雅優美。 風格: 1950年代日本舊膠片電影質感,暖黃偏褐色調,古樸膠片顆粒感與輕微雜訊,老電影膠片划痕與輕微抖動,柔和漫射光,帶有復古懷舊氛圍,電影級打光,淺景深。 第一段(0-15秒): 0-3s:清晨湖邊,古松樹影下,肌肉結實的漁夫伯良正在撒網捕魚,畫面出現優雅金色日文書法特效「伯良」逐筆筆畫浮現,周圍飄散細碎金粉粒子。 3-6s:他抬頭看見松樹枝頭掛著一件閃耀七彩光芒的羽衣。 6-9s:循著湖面看去,絕美的天女正在湖中沐浴,優雅地雙手高捧湖水緩緩淋在自己身上,展現極致古典日式姿態美,畫面出現優雅金色日文書法特效「天女」逐筆筆畫浮現,周圍飄散細碎金粉粒子。 9-12s:伯良拿起羽衣,天女發現後驚慌地用手臂遮掩身體。 12-15s:天女用古典日文羞澀地說:"どうか... 私の衣をお返しください。" 第二段(15-30秒): 15-18s:伯良高高舉起閃耀七彩光芒的羽衣,微笑卻帶點威脅地用英文說:"If you want it back, you have to dance for me first." 18-21s:仍在湖中的天女臉頰微微羞紅,用古典日文說:"そんな... それはあまりにも酷です。" 21-24s:伯良堅持道:"Dance beautifully, and I'll return it." 24-27s:天女無奈只好上岸,在湖邊輕盈跳舞,舞姿如古代神樂般優雅魔幻,粉紅色露肩內襯隨風輕揚。 27-30s:伯良坐在岸邊石塊上,將羽衣掛在自己脖子上,看得完全入迷。 第三段(30-45秒): 30-33s:天女停止跳舞,慢慢走向伯良,眼神曖昧又帶哀求。 33-36s:伯良伸手輕觸她的臉頰,兩人眼神深深交纏,氣氛極致曖昧。 36-39s:天女趁伯良沉醉之際,迅速伸手將掛在他脖子上的羽衣搶回,快速披在自己身上。 39-42s:天女恢復天人該有的高雅自信,用古典日文優雅地說:"このひととき、感謝いたします、麗しき男よ。" 42-45s:天女發出有些詭異而空靈的笑聲,羽衣發出強光,迅速飛昇消失在晨霧之中,伯良伸手想抓住卻只抓到空氣。

Seedance 2.0 AI video prompt: Shot count: 12 | Duration: 15s | Aspect ratio: 16:9

Use <<<Image1>>> (12-panel

Shot count: 12 | Duration: 15s | Aspect ratio: 16:9 Use <<<Image1>>> (12-panel storyboard) as the STRICT visual reference for every character, facial appearance, costume, hairstyle, blindfold, choreography, snowy ancient yamen courtyard, architecture, and lighting. Maintain 100% identical character design throughout. No character drift. No text. No subtitles. No captions. Genre Classic 1990s Hong Kong wuxia fantasy film. Fast-paced cinematic editing, elegant yet brutal wire-fu choreography, explosive martial arts energy, heavy dramatic snowfall, premium live-action realism, Tsui Hark style. Performance The blindfolded heroine in red is extremely dominant and confident in the first 10 seconds — she completely overpowers and humiliates Bao Zheng with graceful, deadly precision. Bao Zheng is brutally beaten and sent flying before his sudden comeback in the final 4-5 seconds. Voice-over (Male, deep, serious traditional Chinese ancient drama narrator voice) At the very beginning (0.0-1.0s): "公元1039年,包拯接受蒙面公主的挑戰。" At the very end (14.0-15.0s): "結局下次分曉!" Music Epic 1990s Hong Kong wuxia soundtrack. Intense Chinese orchestra + powerful percussion, soaring erhu, aggressive taiko drums, thunderous timpani, dramatic brass, rapid strings, emotional choir. Fast tempo 148-158 BPM, constantly escalating, perfectly synced with every punch and impact. Shot 1 (0.0–1.3s) (Follows Panel 1 exactly) Wide crane establishing shot under full moon. Heavy snow falling. Blindfolded heroine in red slowly walks forward, confronting Bao Zheng in front of the ancient yamen. Shot 2 (1.3–2.4s) (Follows Panel 2 exactly) Fast push-in close-up on heroine. She raises her palm into perfect martial arts stance, red blindfold fluttering. Shot 3 (2.4–3.5s) (Follows Panel 3 exactly) She vanishes and explodes forward with lightning-fast punch. Dialogue Heroine (sneering): "Too slow, fool!" Shot 4 (3.5–5.2s) (Follows Panel 4 exactly) Relentless storm of spinning kicks, chain punches, and flowing red sleeves. She overwhelms him completely. Dialogue Heroine (shouting): "Stay down, pathetic!" Shot 5 (5.2–6.4s) (Follows Panel 5 exactly) Handheld violent close-up. Bao Zheng desperately blocks but gets crushed by multiple heavy blows to chest and shoulders, coughing blood. Dialogue Bao Zheng (in pain): "Ugh—!" Shot 6 (6.4–7.8s) (Follows Panel 6 exactly) Final devastating palm strike sends Bao Zheng flying across the courtyard, crashing hard into the snow. Dialogue Heroine (laughing coldly): "How sad!" Shot 7 (7.8–9.0s) (Follows Panel 7 exactly) Slow push-in on Bao Zheng painfully rising from the snow, blood at mouth corner. His expression turns ice-cold. Snow spirals violently around him. Dialogue Bao Zheng (low, menacing): "Finished? My turn now!" Shot 8 (9.0–10.2s) (Follows Panel 8 exactly) Golden energy erupts between his palms. The entire courtyard shakes violently. Dialogue Heroine (shocked): "What...? Impossible!" Shot 9 (10.2–11.3s) (Follows Panel 9 exactly) Bao Zheng unleashes massive invisible shockwave that tears across the courtyard like a tsunami of force. Ultra-wide cinematic shot. Dialogue Bao Zheng (roaring): "KNEEL NOW!!!" Shot 10 (11.3–12.4s) (Follows Panel 10 exactly) Slow-motion side tracking shot. Heroine is helplessly blasted backward through the air, robes whipping wildly. Dialogue Heroine (panicked): "NOOO—!" Shot 11 (12.4–13.6s) (Follows Panel 11 exactly) Violent front impact shot. She slams into the stone wall, creating a huge crater with exploding stone and snow. Dialogue Heroine (screaming in pain): "AAAGHH!!" Shot 12 (13.6–15.0s) (Follows Panel 12 exactly) Slow dolly backward. Heroine drops to one knee, breathing heavily and defeated. Bao Zheng stands tall under the moonlight, robes fluttering as snow falls silently over the destroyed courtyard. Style Photorealistic 1990s Hong Kong wuxia live-action. Hyper-dynamic wire-fu, dramatic moonlight, intense snowfall, explosive VFX energy, realistic cloth and physics, expressive faces, cinematic camera work, shallow depth of field, HDR, 4K. Editing Style Ultra-fast Hong Kong action editing. Cut every 0.8–1.3 seconds in the first 10s. Heavy speed ramps, whip-pans, impact zooms, crash zooms. First 10 seconds focused on heroine's brutal dominance. Final 5 seconds extremely explosive counterattack and reversal.

Seedance 2.0 AI video prompt: se the uploaded image as the exact start-frame reference for the man and woman:

se the uploaded image as the exact start-frame reference for the man and woman: same 1980s wardrobe, faces, hair, glasses, warm film lighting, playful close-up framing, and vintage adventure-comedy tone. A charming bespectacled young man nervously holds a bulky practical laser blaster beside a confident glamorous woman who looks unimpressed but secretly amused. The scene feels like a real 1980s family adventure sci-fi film shot on 35mm, with practical FX only: rubber-suit AI robots, blinking LEDs, smoke, sparks, puppeteered robot arms, no CGI, no modern digital look. 0–3 sec: Start in the same close-up composition. The man grins and whispers, “I told you, I live for danger.” The woman gives him a dry side-eye and says, “You also live with your mom.” 3–6 sec: Behind them, a clunky chrome AI robot rolls into view, red lights blinking, arms wobbling like practical animatronics. The man’s smile freezes. The woman calmly grabs his wrist and pulls the blaster away from his face. 6–10 sec: They duck behind a console as foam sparks pop from the robot. The woman fires one clean laser blast from the practical prop, hitting a hanging cable; the cable drops onto the robot with a burst of smoke. The man stares at her, amazed. 10–14 sec: The robot short-circuits and spins in place. The man softly says, “So… dinner after we save the world?” She smirks, leans close, and says, “Only if you stop pointing that thing at yourself.” They run off together, laughing, adventurous and romantic. Style locks: authentic 1980s film grain, warm tungsten practical lighting, soft vintage lenses, handheld adventure-comedy energy, real actors, real sets, practical smoke and sparks, rubber-suit robots, no CGI, no text overlays, no logos, no subtitles, no modern sci-fi polish.

More use cases

Frequently asked questions

What are the best AI video prompts for retro and vintage video?

The best retro prompts name the recording format and its physical artifacts as a system rather than using vague aesthetic instructions like "vintage feel." "Super 8 film, heavy midtone grain, warm Kodachrome color science, light leak at the left edge, 18fps frame rate stutter" is a camera system specification that produces 1970s-era footage. "VHS, horizontal scan lines, chroma bleeding at edges, oversaturated NTSC primaries, timestamp burned in lower right" produces the 1980s–90s video aesthetic. The format name activates the full artifact bundle simultaneously — every prompt in this gallery uses that approach rather than a filter instruction.

How do I write a retro or vintage video prompt for Seedance 2.0?

Structure the retro prompt in three layers: (1) the recording format and era — "Super 8 film circa 1974," "VHS camcorder footage from 1988," "16mm Kodachrome documentary 1965" — which activates the full artifact grammar of that system; (2) the specific physical artifacts you want most prominent — grain type, scan lines, color bleed, light leak, vignetting, timestamp; (3) the color science of the era — "warm Kodachrome reds and oranges with lifted blacks," "NTSC composite oversaturation, orange skin tones under fluorescent light," "early digital flat highlights, cooled temperature." Those three layers together produce era-accurate footage; omitting any one produces a generic filter look.

Can Seedance 2.0 generate realistic-looking retro and VHS-style video?

Yes. Seedance 2.0 handles retro aesthetics well when the prompt names the recording format and its physical artifacts explicitly rather than using generic "vintage" instructions. "VHS, horizontal scan lines at fixed frequency, chroma bleeding to the right of high-contrast edges, oversaturated NTSC color, consumer-camcorder autofocus hunting, timestamp bottom-right" gives Seedance a complete technical system to render. The same applies to Super 8, 16mm, Hi8, and early digital formats — each has specific artifact signatures that activate era recognition when named precisely. Browse the retro prompts here for examples with preview videos.