Skip to content
PromptMotion

Seedance 2.5Topic · Video

Seedance 2.5 Prompts

Seedance 2.5 prompts from public video posts, paired with the original sources and marked translations. Launched by ByteDance Seed on July 31, 2026, Seedance 2.5 jointly generates audio and video for up to 30 seconds in a single pass.

Cases12
With prompt12
LatestOct 23, 2026

01Results

Seedance 2.5 Prompt Examples

Still from Seoul Summer Night VlogVideo0:30Watch the original
Seedance 2.5Prompt

Seoul Summer Night Vlog

@AIwithkhan · 6,201 likes

Create a 30-second, 1080p ultra-realistic personal home-video showing an ordinary summer evening in the life of a young Korean woman. No reference image. MAIN SUBJECT Young Korean woman in her early 20s, naturally pretty, realistic skin texture, minimal makeup, relaxed and approachable personality. Long black hair loosely tied into a messy side ponytail with a few loose strands around her face. Wearing a fitted pastel-blue short top, loose cream pajama-style pants, black sneakers and a simple silver necklace. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout the entire video. SETTING A quiet older Seoul residential neighborhood during a warm summer evening. Narrow concrete lanes, small houses, potted plants, bicycles, old walls, utility poles, overhead wires, a tiny neighborhood bakery, a public water tap and large leafy trees casting shadows across the street. Everything should feel lived-in, ordinary and peaceful. CAMERA / VISUAL AESTHETIC Raw personal footage casually recorded by a friend on an early-2000s consumer DV camcorder. Strong handheld shake, imperfect framing, autofocus hunting, exposure shifts, occasional motion blur, faded colors, soft digital detail, mild noise, accidental zooms and natural camera imperfections. — OUTSIDE THE HOUSE She steps outside carrying a small reusable shopping bag. She locks the door, adjusts her messy ponytail and looks toward the camera with a relaxed smile. — BAKERY STOP She reaches a tiny neighborhood bakery and buys a warm pastry. She steps outside, takes her first bite and immediately smiles because it tastes good. She notices her friend filming and holds the pastry toward the camera playfully before taking another bite. — WALKING HOME She continues down the narrow street while eating. A neighborhood cat follows her for a few steps. She notices it, crouches down and gently pets it. — SMALL ACCIDENT She walks beneath a large tree when a few leaves fall onto her hair. She stops, looks confused, then realizes what happened and laughs. — QUIET MOMENT She reaches a low concrete wall beside the street and sits down for a moment. — FINAL MOMENT She stands up and continues walking home.

Still from Frozen Time and Rewind in a 1950s DinerVideo0:30Watch the original
Seedance 2.5Prompt

Frozen Time and Rewind in a 1950s Diner

@techhalla · 2,879 likes

Photorealistic cinematic 1950s American diner, chrome stools, red vinyl, neon glow and checkerboard floor, shot with modern lived-in realism and soft natural window light. Subtle handheld texture, warm practicals, rich period detail, heavy film grain. 0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at the counter, calm and slightly amused, slowly sipping a tall thick milkshake through a straw. Behind her a young waitress in classic uniform approaches with a tray of eggs and bacon in one hand and a full glass coffee pot in the other. An older lady starts rising from a nearby booth. 4-8s: [Dynamic Tracking] The older lady collides hard into the waitress. Tray, plate, eggs, bacon and coffee pot explode upward in chaotic slow motion. Coffee erupts into long liquid ribbons and perfect suspended droplets. Camera immediately begins a smooth continuous orbit around the impact. Time locks completely at the peak of the spill. Every face freezes in pure shock. Only the girl at the counter keeps moving, completely unfazed. 8-17s: [Slow 360° Orbital] Camera glides in a full elegant orbit through the frozen diner. Coffee hangs in mid-air as glassy ribbons and spheres with perfect volume and surface tension. Bacon strips, eggs and the spinning tray float weightlessly. Patrons and waitress remain locked in startled expressions. The girl at the counter takes one slow, deliberate sip, eyes half-lidded, almost bored, while the entire frozen world (except her) begins an elegant reverse: every droplet, every piece of food and every person rewinds smoothly back to the exact starting positions. 17-24s: [Medium Shot] Rewind lands perfectly. Waitress stands balanced again with tray and coffee pot. The girl lifts her eyes, raises two fingers in a small casual gesture and softly calls the waitress by name. The waitress turns toward her just before the older lady begins to stand, completely avoiding the collision. A tiny private smile crosses the girl’s face. 24-30s: [Extreme Close-Up] Hard cut to her face as she takes one last slow sip. Soft knowing smile, eyes almost closed in quiet satisfaction, like she has done this a hundred times. Shallow depth of field, creamy bokeh of the neon diner behind her. Photorealistic, ultra-detailed fluid physics, perfect motion blur only on moving elements, stable characters, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence, high rewatch value.

Still from Mini DV Coffee ASMR VlogVideo0:30Watch the original
Seedance 2.5Prompt

Mini DV Coffee ASMR Vlog

@Strength04_X · 835 likes

CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bright kitchen morning light. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic. STYLE: Cozy coffee-prep vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments. Focus on satisfying sounds: bean grinder whirring, portafilter tamping, steam wand hissing, cup clinking, milk frothing. SUBJECT: Young man in his mid-20s, plain t-shirt, hair slightly tousled, minimal accessories. Calm, focused energy while making his morning coffee. SETTING: Small kitchen counter with an espresso machine on a bright morning. Natural daylight, coffee beans and a mug nearby, quiet atmosphere. STORYBOARD: → (3s, propped medium shot) Places camera on the counter, switches on the machine. "Morning coffee, the proper way." → (3s, overhead shot) Grinds fresh coffee beans, fine grounds falling into the portafilter. → (3s, close-up) Tamps the grounds down firmly and evenly. → (3s, handheld shot) Locks the portafilter into the machine. "Here we go." → (3s, detail shot) Espresso streams slowly into a small cup. No dialogue. → (3s, medium shot) Pours cold milk into a small steel pitcher. "Time for the milk." → (3s, macro shot) Steam wand hissing as it froths the milk. → (3s, propped shot) Pours frothed milk carefully over the espresso, forming light layers. → (3s, warm ending shot) Holds the finished cup, takes a small sip, satisfied smile. "That's exactly what I needed." → (3s, final shot) Reaches toward camera, still holding the cup. "See you later." Hand covers lens as recording ends. AUDIO NOTES: Natural kitchen ambience — grinder whirring, tamping, steam hissing, milk pouring should be clearly audible. Dialogue quiet and casual. REALISM NOTES: Authentic body language, natural blinking, genuine focused smiles, occasional careful pauses while pouring, imperfect framing, focus breathing, bright morning light shifts. Should resemble a genuine personal coffee vlog on a consumer camcorder, not a commercial or AI-generated production.

Still from Two-Idol K-pop MV, Shot by ShotVideo0:30Watch the original
Seedance 2.5Prompt

Two-Idol K-pop MV, Shot by Shot

@Just_sharon7 · 551 likes

30-second ultra-realistic K-pop MV featuring two young East Asian women with flawless synchronization, cinematic lighting, glossy skin, realistic hair and fabric physics, natural body motion, and 4K live-action quality. Vibrant hot pink, electric blue, and silver color palette. 0–2s: Wide shot in a bright circular pink studio with reflective floor. Pink-haired woman (left) and black-haired woman (right) perform energetic opening pose and synchronized dance. 2–4s: Medium close-up of the black-haired woman on a blue spotlight stage, confidently pointing at the camera. 4–6s: Pink-haired woman dances before shimmering blue-silver tinsel curtains, dramatic hair flip and fluid arm movements. 6–8s: Back to the pink studio. Both perform synchronized choreography with sharp arm waves, hip sways, and strong formations. 8–10s: Extreme close-up of both faces against a blue background, glossy makeup, subtle smiles, and direct eye contact. 10–14s: Solo shots at the tinsel backdrop. Pink-haired woman mouths lyrics and gestures confidently, followed by the black-haired woman with relaxed jacket styling. 14–18s: Pink studio. Coordinated jacket choreography, hair flips, powerful synchronized dance, ending hands-on-hips. 18–22s: Glamour close-ups. Black-haired woman under glittering bokeh lights, then pink-haired woman with wind-blown hair against a soft pink background. 22–24s: Blue spotlight stage. Mirrored black-haired performer effect with synchronized spins and flowing hair. 24–26s: Both walk confidently toward the camera in front of shimmering tinsel curtains, reflections visible on the floor. 26–29s: Final synchronized dance and ending pose in the pink circular studio, standing together and looking into the camera. Style: Hyper-realistic live action, Seedance 2.5-quality motion realism, perfect lip sync, natural weight shifts, flowing hair, realistic fabric simulation, polished K-pop music video cinematography.

Seedance 2.5X post · plays on click
Video0:30Watch the original
Seedance 2.5Prompt

A consistent character in a self-shot New York vlog

@EvoLinkAi · 385 likes

Character sheet created by GPT Image 2.5: IMPORTANT — IDENTITY LOCK: The uploaded reference image is the definitive identity reference. Reproduce the EXACT SAME PERSON throughout the entire character sheet. Do NOT redesign, beautify, reinterpret, or replace the character. Preserve with maximum accuracy: exact facial identity, facial structure and proportions, eyes, eye shape and iris color, eyebrows and natural brow shape, nose shape and proportions, lips, mouth shape and fullness, cheeks, jawline and chin, skin tone and natural skin texture, age appearance, hairline, exact hair color, length, texture and hairstyle, body proportions and physique, distinctive facial characteristics. CHARACTER SHEET LAYOUT: Create one clean, professional reference-board image containing: large front portrait / face close-up, front view, 3/4 left view, 3/4 right view, left profile, right profile, back view, full-body front view, full-body 3/4 view, full-body side view, full-body back view, neutral expression, natural smile, soft smile, looking left, looking right, eye close-up, eyebrow close-up, nose close-up, lips close-up, hair close-up, accessories close-up, outfit / clothing reference, color palette / skin-tone reference. CONSISTENCY: Every panel must show the SAME person. Keep facial identity, proportions, hairstyle, skin tone, body shape, and physical characteristics consistent across every angle, pose, and expression. For views not clearly visible in the reference, intelligently reconstruct the character while staying strictly faithful to the visible reference. Do not invent major distinguishing features. PRESENTATION: Premium professional film-production character bible / modeling reference sheet. Clean editorial layout. Neutral studio background. Soft realistic studio lighting. Sharp facial details. Natural skin pores and texture. Individual hair strands. Realistic fabric and accessories. Accurate human anatomy. Consistent camera perspective. Clean thin borders between panels. Professional labels underneath each view. Minimal elegant typography. High-end fashion / model reference aesthetic. PHOTOREALISM: Ultra-photorealistic. Real human appearance. Natural skin texture. Realistic eyes. Physically accurate hair. Natural shadows. Realistic proportions. No CGI appearance. No plastic skin. No doll-like face. No artificial beauty-face replacement. NEGATIVE PROMPT: different person, different face, face morphing, identity drift, altered facial structure, different eyes, different nose, different lips, different jawline, different skin tone, different hairstyle, inconsistent body proportions, duplicate person, distorted anatomy, asymmetrical face, plastic skin, waxy skin, CGI, 3D render, cartoon, anime, illustration, over-beautification, excessive makeup, unrealistic eyes, blurry face, low detail, extra fingers, missing fingers, malformed hands, bad anatomy. OUTPUT: One complete, highly detailed professional CHARACTER CONSISTENCY SHEET in a single image, suitable as a master reference for generating consistent images and videos of this character. Video created by Seedance 2.5: SCENE: A day in New York shot entirely by the subject herself: waking in her hotel suite, coffee, getting ready, out into the city, back to the room at night. ACTIVE REFERENCES: @image1 — the hotel suite. Curved cove ceiling with warm LED coving, deep red carpet, cream walls, two black organic sculptures above a light wood headboard, white bedding with red pillows, twin bedside lamps, pale sofa, oval coffee table, sheer curtains, dark door. @image2 — the subject. Young woman, shoulder-length wavy blonde hair with curtain bangs and highlights, light freckles, thin gold necklace, silver ring, dark brown off-the-shoulder knit with white diamond-stripe pattern. 100% matches the reference. CAMERA OWNERSHIP LOCK: Only two positions exist. HELD: arm extended, camera 0.4–0.7m from her face, visible arm tension, tilt and step-bounce. PROPPED: camera on a surface she placed it on, crooked and fixed, with her moving in and out of frame. No operator shots, no tracking, nothing she could not have filmed alone. FORMAT: Eight shots, 30s, seven hard cuts, no fades. Real-time. 0–4s SHOT 1 — PROPPED, morning room. Camera on the sideboard 3m from the bed at 1.1m, static and tilted. The suite matches @image1: cove light on, curtains half open, cool daylight across the red carpet. @image2 is visible at 0.0s, sitting up on the bed edge. She rubs her face and says to the running camera: “It’s seven. In New York. Why am I awake.” She stands and walks out screen-right. HARD CUT. 4–7s SHOT 2 — HELD, window light. Arm’s length, above eye line. She pulls the curtain, squints at the street below, then looks into the lens: “Okay. It’s actually happening.” Arm wobble throughout. HARD CUT. 7–11s SHOT 3 — PROPPED, coffee. Camera on the oval coffee table, low, looking up past a cup. She sits into frame, pours, tastes, and says: “Hotel coffee. We’ll fix that outside.” Steam bends in the light. HARD CUT. 11–15s SHOT 4 — HELD, mirror. Camera at chest height reflected in the suite mirror. She works through her hair with the other hand. At 13s: “This is as good as it gets. Let’s go.” HARD CUT. 15–18s SHOT 5 — HELD, leaving. Camera held low at waist height, turned forward. She crosses the red carpet to the door. She opens it and corridor light floods the frame. Off-frame: “Downtown first.” HARD CUT. 18–22s SHOT 6 — PROPPED, street. Camera on a stoop rail, static and crooked. A New York block behind her: brownstone steps, fire escapes, yellow cabs, steam from a vent. She walks in from screen-left, stands in frame, and says: “Look at this street.” Then walks to the lens and takes it. Passers-by cross the foreground. HARD CUT. 22–26s SHOT 7 — PROPPED, diner. Camera on the counter behind a plate, looking up. She sits into frame, takes a bite, eyes widen, and says: “Okay, that’s the one.” She laughs and keeps eating. HARD CUT. 26–30s SHOT 8 — HELD, night, back in the room. She lies back across the white bedding, hair spread, in the brown knit again. Bedside lamps and cove light are the only sources. Into the lens: “Twenty thousand steps. Everything hurts.” Softer: “Same time tomorrow.” She waves as she lowers the camera. 30.0s black. SPEECH: Only the quoted lines are spoken, at the timings given, all in her voice. Lips still at all other times. No voiceover, no second speaker, no offscreen voices. Delivery is casual, unrehearsed, mid-breath, sometimes trailing off. CONTINUITY: The suite matches @image1 in both interior sequences. Hair, necklace, ring, face, body proportions, and outfit details remain identical throughout. PHYSICS: Loose knit slides on the shoulder with every arm movement. Wavy hair lags a frame behind head turns. Bedding creases under her weight. Step energy is visible in every HELD frame. LIGHTING: Shots 1–4 use cool daylight from the curtains as key and warm cove LED as fill. Shot 5 uses corridor light. Shots 6–7 use hard street daylight and warm diner practicals. Shot 8 uses lamps and cove light only. AUDIO: Diegetic only, from the same camera — room tone, footsteps, door, traffic, sirens, steam vents, diner clatter, and wind. Ambience ducks under her lines. No music. LOCKS: Photoreal live action, 4K detail, fine grain, warm consumer-camera color, mild rolling shutter and auto-exposure hunting. She is the only person who speaks. Background figures are anonymous and unfocused. No subtitles. Want more usecases prompts? https://t.co/r2MeU0NWLB

Seedance 2.5X post · plays on click
Video0:30Watch the original
Seedance 2.5Prompt

A duel between gothic swordswomen from an image style reference

@aimikoda · 324 likes

Premium dark fantasy 2D anime cinematography fused with gothic ink illustration, high-sakuga sword choreography and experimental action filmmaking. Preserve the reference aesthetic of intricate black linework, rough hand-drawn textures, charcoal-gray shading, muted violet skin tones, elaborate gothic silhouettes and aggressive neon pink, acid green and prismatic highlights. Ultra-fast, brutally aggressive swordsmanship with relentless blade exchanges, acrobatic counters, spinning slashes, sudden reversals, impossible footwork and explosive multi-hit combinations, maintaining constant offensive pressure from both fighters. Every clash produces razor-sharp neon streaks, violent chromatic sparks, fractured ink splashes and brief flashes of saturated light that illuminate the surrounding darkness. Radical cinematic perspectives combine ground-skimming tracking shots, aggressive Dutch angles, extreme foreshortening, rapid orbital rotations, blade-following whip pans, sudden perspective inversions and seamless camera movements threading through crossing swords. Insert lightning-fast detail cuts of narrowed eyes, tightening fingers, twisting wrists, grazing blades and sparks scattering across faces, immediately returning to ferocious wide-angle combat. Dramatic foreground occlusion, near-lens blade strikes, shifting focal distances and rapid depth transitions create visceral immersion. Dark atmospheric voids, drifting ash, torn feathers and vibrating debris react to the force of each exchange. Precise silhouette control, strong visual rhythm and high-contrast graphic compositions preserve clarity even during overwhelming bursts of speed. No slow motion, no idle posing, no pauses between attacks. Every movement flows directly into another attack, parry or counterattack. Hand-drawn anime expressiveness and premium 2.5D cinematic depth preserve the original illustration style without turning the characters into realistic CGI. Two gothic elven swordswomen engage in a relentless duel inside a ruined cathedral swallowed by darkness. The black-haired warrior with her feathered crown attacks with a prismatic blade, immediately colliding with the silver-haired warrior's neon sword. They explode into a succession of impossibly fast sword exchanges, spinning counters, airborne reversals and close-range blade locks that instantly break into new attacks. The camera spirals tightly around their crossing weapons, dives beneath sweeping strikes, whips past their faces and follows a blade within inches of the lens. Sudden close-ups capture furious expressions, razor-thin near misses and sparks streaking across their skin. Both warriors continuously reverse the advantage through increasingly elaborate combinations, ricocheting off broken pillars, intercepting attacks from impossible angles and chaining acrobatic movements into ferocious counterstrikes. Every impact briefly floods the monochromatic environment with violent pink, green and rainbow light. The battle escalates without interruption, ending mid-combination as both warriors launch simultaneous devastating attacks directly toward each other.

Seedance 2.5X post · plays on click
Video0:30Watch the original
Seedance 2.5Prompt

A continuous conversation across a galactic port

@aimikoda · 238 likes

A painterly animated romantic drama follows a young courier and a young mechanic racing through a decaying galactic port during their final minutes together. The Courier wears a weathered crimson travel coat and carries one small flight bag; the Mechanic wears a dark work jacket marked by luminous machine dust. Keep their faces, clothing, and bag consistent throughout. Use an Arcane-inspired visual style: sculpted 3D characters finished with expressive hand-painted textures, visible brushwork, graphic silhouettes, fractured colored light, atmospheric depth, painterly motion smears, selective frame skipping, and explosive fluidity during major movements. Build a lived-in galactic frontier of patched starships, analog machines, strange travelers, service automatons, rain-dark metal, and monumental industrial architecture. Use deep blue shadows, corroded copper, crimson fabric, cyan engines, and warm gold skin light. The conversation begins on the first frame and ends on the final frame. Every timed beat contains dialogue. The Courier and Mechanic speak directly to each other in natural American English, with intimate restraint and precise lip sync. Carry a breath or vocal overlap across each cut so the conversation never restarts or leaves an empty pause. 0-4 seconds: A magnetic tram races above an ocean city built vertically into black cliffs beneath an immense ringed planet. The Courier and Mechanic stand on its exposed rear platform as rain bends horizontally and starships rise around them. The Courier looks across the impossible skyline rather than at him: {This city only looks beautiful when we’re escaping it.} 4-9 seconds: The tram tears through a crowded docking tower without stopping. They jump together onto a suspended freight platform moving in the opposite direction, landing hard among swaying cargo and startled alien travelers. The Mechanic catches her before she falls: {We spent years dreaming of this, and now you’re leaving alone.} 9-13 seconds: They enter a transparent customs sphere just as its artificial gravity fails. Travelers, luggage, droplets, and service machines drift upward. The couple floats apart until the Courier catches his sleeve and pulls herself close enough to meet his eyes: {You had years to give me reasons to stay.} 13-17 seconds: Gravity returns. Hard cut on their impact to a magnetic elevator dropping through the center of a colossal shipyard. Half-built vessels and welding constellations streak upward outside the glass. The Mechanic watches their reflections standing together instead of looking at her: {I thought loving you quietly might be enough.} 17-21 seconds: The elevator opens inside a cathedral-sized orbital greenhouse suspended between two towers. Turbulence from an arriving ship tears thousands of luminous seed petals into a spiraling current. They push through the glowing storm, the Courier running backward for a moment so she can face him: {I waited for you to choose me out loud.} 21-25 seconds: They emerge onto the greenhouse roof as a narrow service arm rotates above the city to meet her departing skiff. The couple steps onto the moving arm together, surrounded by rain, drifting petals, and the immense ocean far below. As the arm carries them toward the ship, the Mechanic finally holds her gaze: {I chose you every day, just never bravely enough.} 25-30 seconds: The service arm aligns with the skiff for only a moment. The Courier steps aboard while the Mechanic remains on the arm; they keep their hands linked as the skiff immediately begins to rise. Distance slowly pulls their fingers apart. Suspended above the glowing city, she calls through the wind: {Then say it before the sky takes me.} The Mechanic runs to the end of the arm as the skiff climbs beyond his reach. He finally shouts: {I love you.} She hears him, but the clouds swallow the skiff before she can answer. Cut to black on his final word. No BGM. Use only dialogue, rain, tram vibration, cargo impacts, crowd voices, gravity-system pulses, elevator resonance, rushing petals, rotating machinery, engines, breath, and wind. Keep environmental sound beneath the voices. No subtitles, captions, logos, title cards, or graphic overlays.

Seedance 2.5X post · plays on click
Video0:30Watch the original
Seedance 2.5Prompt

Three friends explore a mountain village

@Alina_with_Ai · 96 likes

Create a highly realistic 30-second cinematic smartphone vlog featuring THREE young adult women exploring a beautiful small American mountain village. REFERENCE IMAGES & IDENTITY: Use the 3 uploaded reference images as identity references. REFERENCE IMAGE 1 = MAIN VLOGGER. REFERENCE IMAGE 2 = FRIEND 1. REFERENCE IMAGE 3 = FRIEND 2. Preserve each woman's facial identity, facial features, hairstyle, skin tone, body proportions and overall appearance consistently throughout the entire video. Never swap or mix their identities. MAIN VLOGGER — GIRL 1: A beautiful young adult woman with the exact identity and facial appearance from Reference Image 1. She is the main character and the person filming the entire vlog. DRESSING: She wears a stylish fitted cream/ivory knit top, high-waisted light-blue straight-leg jeans, an elegant beige cropped trench jacket, clean white sneakers, and a small tan leather crossbody bag. Add delicate gold jewelry, a simple gold necklace and small hoop earrings. Her overall fashion should feel classy, modern, feminine and effortlessly stylish, like a fashionable young woman spending a weekend in a beautiful American mountain village. Her hair, makeup and outfit remain exactly consistent throughout the entire video. FRIEND 1 — GIRL 2: Use the exact identity from Reference Image 2. DRESSING: She wears a stylish fitted sage-green sweater, high-waisted off-white wide-leg pants, a light beige cardigan, clean white sneakers and a small brown shoulder bag. Add minimal elegant gold jewelry. She has a naturally stylish, relaxed and feminine appearance. FRIEND 2 — GIRL 3: Use the exact identity from Reference Image 3. DRESSING: She wears a stylish dusty-blue fitted long-sleeve top, high-waisted dark-wash straight-leg jeans, a light cream denim jacket, clean white sneakers and a small black crossbody bag. Add simple elegant earrings. All three women must have DIFFERENT outfits, colors and accessories, but their outfits should look naturally coordinated as a stylish group. Do NOT use gymwear, athletic clothing, formal dresses or overly revealing clothing. LOCATION: A beautiful small American mountain village during a bright, fresh morning. The village has beautiful narrow winding streets, charming wooden houses, cozy front porches, stone pathways, flower gardens, wooden fences, small local shops, trees and large green mountains surrounding the village. The environment should feel peaceful, authentic, naturally lived-in and photorealistic. A few local residents and small children can be naturally visible in the background, playing or walking around the village. Keep the background uncrowded. CAMERA & VLOG STYLE: The main woman holds a modern smartphone herself throughout the vlog and records in authentic arm's-length selfie mode. The camera must feel like a real personal smartphone vlog. Natural handheld movement, subtle hand movement, realistic walking motion, slight imperfect framing, natural autofocus adjustments and tiny exposure changes. The main woman must clearly be the person filming. Never show a camera operator. The smartphone itself should never be visible in the frame. Keep all three women visually consistent throughout the entire video. STORYBOARD — EXACTLY 30 SECONDS: CUT 01 — 0:00–0:05 MORNING VILLAGE INTRO The main woman walks along a beautiful narrow village street while holding the smartphone in selfie mode. Her two female friends walk naturally beside and slightly behind her. She smiles toward the camera and says naturally: “Good morning from this little village!” The mountains and charming houses are visible behind them. Natural walking and friendly expressions. CUT 02 — 0:05–0:10 EXPLORING THE VILLAGE The main woman continues walking and briefly turns the phone toward the beautiful surroundings. Show narrow streets, wooden houses, flower gardens, small porches, trees and mountains. Small children can be seen naturally playing nearby. She turns the phone back toward herself and her friends. All three women smile and casually interact while walking. CUT 03 — 0:10–0:14 THE CAR MOMENT A beautiful classic American car naturally drives past them on the narrow village street. The car passes reasonably close but safely. The main woman notices it, turns the phone slightly toward the car and smiles. She says: “So pretty!” Her friends react naturally and smile. The moment should feel spontaneous, not staged. CUT 04 — 0:14–0:20 WALKING TO THE COFFEE SHOP The three women continue walking together through the beautiful village. They casually talk, laugh and enjoy the morning. Show several cinematic walking angles while maintaining the authentic smartphone-vlog feeling. They approach a charming small local coffee shop with a warm, cozy exterior. Use a natural jump cut as they enter the café. CUT 05 — 0:20–0:25 COFFEE Inside the cozy local coffee shop, the three women order coffee. Show the main woman receiving a freshly prepared coffee. She smiles toward the phone. The friends receive their coffees as well. They walk outside together. Keep their faces, outfits, hairstyles and identities perfectly consistent. CUT 06 — 0:25–0:30 MOUNTAIN COFFEE MOMENT The three women stand outside the coffee shop with their drinks. The main woman holds the smartphone in selfie mode and takes a sip of her coffee. Her two friends stand naturally beside her. The beautiful mountain landscape and village street are visible behind them. She smiles and says: “Honestly, I love this place.” The camera naturally turns slightly toward the village and mountains before ending. VISUAL STYLE: Ultra-photorealistic live-action. Natural human movement. Realistic skin texture. Realistic hair movement. Natural facial expressions. Realistic walking biomechanics. Authentic smartphone camera quality. Beautiful bright morning daylight. Natural shadows and reflections. Cinematic but still believable as a personal travel vlog. Professional visual quality without looking like a commercial. AUDIO: Natural diegetic sound only: footsteps, light wind, birds, distant village sounds, children playing, car passing, café ambience, coffee cup sounds, natural conversation. No background music. No narrator. No subtitles. No artificial voice-over. CONTINUITY: Keep all three women exactly consistent throughout the entire video. No identity changes. No face swapping. No hairstyle changes. No clothing changes. No accessory changes. No age changes. No duplicated people. The main woman always remains the person holding and operating the smartphone. NEGATIVE PROMPT: No bicycles. No motorcycles. No main male character. No camera operator. No visible smartphone. No selfie stick. No CGI. No animation. No cartoon style. No artificial-looking faces. No distorted faces. No distorted hands. No extra fingers. No duplicated people. No identity mixing. No face morphing. No changing outfits. No changing hairstyles. No changing accessories. No futuristic buildings. No crowded city. No unrealistic cars. No impossible physics. No excessive camera shake. No slow motion. No dramatic action scenes. No subtitles. No text. No logos. No watermark.

Seedance 2.5X post · plays on click
Video0:30Watch the original
Seedance 2.5Prompt

A fish market frozen in time and rewound

@Ankit_patel211 · 16 likes

Photorealistic cinematic 1970s Mediterranean seaside fish market, colorful striped awnings, weathered stone streets, overflowing seafood stalls, hanging lanterns, wooden crates, bright coastal sunlight, lively crowds, fluttering seagulls, realistic handheld cinematography, rich environmental detail, heavy natural film grain. 0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at a tiny outdoor café table beside the bustling market, calmly eating lemon gelato. Around her, energetic fishmongers shout prices while customers negotiate loudly. A cheerful vendor walks through the crowd carrying a massive tray stacked with fresh fish, shrimp, octopus, lemons and a bucket of crushed ice. An excited tourist suddenly rushes backward to photograph the harbor. 4-8s: [Dynamic Tracking] The tourist slams into the vendor. Fish, ice, lemons, trays, buckets and seawater explode into the air in spectacular slow motion. Hundreds of ice cubes sparkle in sunlight while silver fish tumble through space. The camera instantly begins a fast continuous orbit around the collision. Time freezes at the exact peak of the chaos. Every person and every seagull stops completely. Only the young woman continues enjoying her gelato without the slightest concern. 8-17s: [Slow 360° Orbital] Camera glides elegantly through the frozen marketplace. Water hangs as crystal ribbons and suspended droplets. Fish, shrimp, octopus, lemons, ice cubes, baskets and wooden crates float weightlessly with incredible realism. Market vendors, tourists and children remain frozen in exaggerated expressions. The young woman calmly takes another spoonful of gelato while the entire frozen world except her begins smoothly rewinding. Every droplet, every fish, every crate, every person and every flying bird retraces its path perfectly back to the starting positions. 17-24s: [Medium Shot] The rewind finishes flawlessly. The vendor once again carries the fully loaded tray. The young woman casually points toward the rushing tourist with a tiny smile. The vendor instinctively steps aside just before the collision would have happened. Disaster completely avoided. Nearby customers never realize anything almost occurred. 24-30s: [Extreme Close-Up] Hard cut to her face as she finishes the final spoonful of gelato. A quiet knowing smile appears while the lively market continues normally behind her. Warm sunlight, shimmering sea reflections, soft coastal breeze, creamy cinematic bokeh. Photorealistic, ultra-detailed fluid simulation, realistic fish and ice physics, physically accurate water behavior, cinematic motion blur only on moving elements, stable character identity, vibrant Mediterranean atmosphere, feature-film quality, heavy natural film grain, seamless temporal coherence, extremely high rewatch value.

Seedance 2.5X post · plays on click
Video0:15Watch the original
Seedance 2.5Prompt

The Patriarch: a cinematic vault portrait

@TheJumbledSoul · 0 likes

GLOBAL STYLE Photoreal cinematic portraiture, 35mm film emulation, heavy organic grain, halation blooming off highlights, 180-degree shutter, no digital sharpening. Aspect 9:16 vertical. Near-black frame with deep teal in the shadows. Colour is rationed: the red rims of his eyes, the flush at his nose and mouth, the raw pink at his fingertips, tarnished brass, and the orange ember of the cigarette. Everything else is lampblack, slate and vellum. NOT a clean CGI render. NOT plastic skin sheen. NOT golden-hour warmth. NOT symmetrical poster framing. NO music, NO narration, NO subtitles, NO on-screen text. SCENE In a lightless vault, an inhuman moneylender rolls a cigarette, turns seven brass lenses onto the viewer, enters one token into his ledger and tells them what it means. CHARACTERS THE PATRIARCH, inherited exactly from @[char ref]: chalk-white translucent skin speckled and veined in carbon black, lidless eyes with golden sclera, hairline vertical pupils and raw red rims, velvet-clad horns swept back low from the temples, obsidian scales along the cranial ridge, seven brass ocular lenses on micro-articulated hydraulic arms mounted at his cheekbones and temples, unnaturally long arms with elongated fingers, tarnished silver signet rings, soot-black double-breasted wool frock coat with velvet trim and dead crimson lining. Ignore the reference's annotation panels, callout text and margin studies. His horns stay dark and swept back and never become pale curved bull horns. He is the only figure in the film. LOCATION An opium vault of wet black stone. A cast iron stool at centre. At screen-right, a slender tripod table carrying an inverted human skull used as a coin tray, heaped with brass tally tokens, and a black beeswax incense burner beside it. The floor is standing water over flagstones and holds a broken reflection. Beyond two metres in any direction the vault is absolute black with no visible walls, ceiling or furniture. FIRST FRAME AND BLOCKING The Patriarch is seated, centred at 50 percent from frame left, his head at 30 percent down, facing camera. His hands are raised at chest height, 50 percent from left and 55 percent down. The tripod table stands at 82 percent from frame left, 70 percent down. He never stands, never leaves the stool, and never turns away from camera. The camera stays in front of him for every shot. SHOT-BY-SHOT BREAKDOWN Shot 1, 0.0 to 4.0s. Extreme close-up on his hands. He rolls the last turn of the cigarette closed, seals it against his lower lip, and lights it from a match struck below frame. The ember catches and blooms. That is the only action. Hard cut. Shot 2, 4.0 to 8.0s. Tight low three-quarter on his left cheekbone, his eye soft behind a foreground brass barrel. The seven lens arms deploy in sequence and nothing else in frame moves. At 4.3s lens 1 telescopes out and its barrel rotates and locks. At 4.8s lens 2. At 5.3s lens 3. At 5.8s lens 4. At 6.2s lens 5. At 6.6s lens 6. At 7.0s lens 7 locks and all seven stand extended and aimed past the camera. Focus racks off the brass onto the golden sclera behind it. Hard cut. Shot 3, 8.0 to 11.5s. Close on the skull coin tray at screen-right, brass tokens catching the light. His long arm enters from frame left and crosses the entire width of the shot, elongated fingers pinching a single tally token. He sets it onto the pile and withdraws the arm. That is the only action. Hard cut. Shot 4, 11.5 to 15.0s. Low frontal medium, his head, shoulders and hands in frame, cigarette burning between two fingers. He raises his head into the overhead light, the golden sclera catch it, and he speaks directly into the lens. Delivery is dry, unhurried, upper-class English, low and clinical, the reaction arriving a half-beat late: {All debts return.} He holds the look after the line ends. OPTICS Shot 1, 85mm macro at hand height. Shot 2, 85mm, camera below his jawline. Shot 3, 50mm at table height, level with the tokens. Shot 4, 40mm, camera below his eyeline so he reads far taller than the viewer. Shallow focus throughout with something soft in the foreground and nothing resolvable behind him. One slow mechanical move per shot, always a push in, never a pull back, never handheld. PHYSICS Each brass lens rides a telescoping hydraulic arm anchored at the cheekbone; an arm extends, the barrel rotates to aim, the joint locks. They deploy one at a time, never together, and stay attached for the rest of the film. His eyes have no lids; a translucent brille membrane sweeps horizontally across each eye and back at a slow natural rate. The incense holds one thin vertical needle of white smoke that widens into haze where it crosses the light, and bends only when he speaks. Heavy wool holds its folds and does not flutter. The cigarette ember brightens on nothing but its own burn. Standing water ripples only when something touches it, and nothing touches it. LIGHTING One hard source hangs directly above him and falls straight down as a visible shaft, its edges defined by incense haze. It carves the crown of his head, the horn tips and the lens cluster, and its falloff is steep enough that the vault two metres behind him is pure black. The cigarette ember is the only other light and throws warm bounce up onto his jaw and the undersides of his hands. The crimson lining shows only as a low ember where the coat folds open. No fill, no rim from behind, no practicals in shot. AUDIO The dead air of a stone vault under a low sub-bass hum. A distant drip into standing water. Paper rustling under his fingers, a match striking, ring metal ticking against ring metal, seven hydraulic joints ratcheting in sequence, one flat click as the token lands, then a held silence before he speaks. Precise lip sync on the single line. NO music, NO narration, NO subtitles.

02How-to

How to Write Seedance 2.5 Prompts

These steps use the capabilities described in ByteDance Seed’s launch announcement and project page, linked in the sources section. Seedance 2.5 jointly generates audio and video and supports multimodal references, extension and timestamp-level editing.

01

Plan the audio and video together

Describe the video and its audio together. Seedance 2.5 supports up to 30 seconds per generation in a single pass and multi-round extension.

02

Choose the reference inputs

A single pass supports up to 30 images, 10 video clips and 10 audio clips. Supported reference types include clay renders, motion and creative references.

03

Specify the time and kind of edit

Use timestamps when describing an edit. Supported controls include timestamp-level editing, green screen, camera perspective and reference-based editing.

03Copyable · quoted verbatim

Seedance 2.5 Prompts from Public Sources

Template · Seoul Summer Night VlogQuoted verbatim
Create a 30-second, 1080p ultra-realistic personal home-video showing an ordinary summer evening in the life of a young Korean woman. No reference image. MAIN SUBJECT Young Korean woman in her early 20s, naturally pretty, realistic skin texture, minimal makeup, relaxed and approachable personality. Long black hair loosely tied into a messy side ponytail with a few loose strands around her face. Wearing a fitted pastel-blue short top, loose cream pajama-style pants, black sneakers and a simple silver necklace. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout the entire video. SETTING A quiet older Seoul residential neighborhood during a warm summer evening. Narrow concrete lanes, small houses, potted plants, bicycles, old walls, utility poles, overhead wires, a tiny neighborhood bakery, a public water tap and large leafy trees casting shadows across the street. Everything should feel lived-in, ordinary and peaceful. CAMERA / VISUAL AESTHETIC Raw personal footage casually recorded by a friend on an early-2000s consumer DV camcorder. Strong handheld shake, imperfect framing, autofocus hunting, exposure shifts, occasional motion blur, faded colors, soft digital detail, mild noise, accidental zooms and natural camera imperfections. — OUTSIDE THE HOUSE She steps outside carrying a small reusable shopping bag. She locks the door, adjusts her messy ponytail and looks toward the camera with a relaxed smile. — BAKERY STOP She reaches a tiny neighborhood bakery and buys a warm pastry. She steps outside, takes her first bite and immediately smiles because it tastes good. She notices her friend filming and holds the pastry toward the camera playfully before taking another bite. — WALKING HOME She continues down the narrow street while eating. A neighborhood cat follows her for a few steps. She notices it, crouches down and gently pets it. — SMALL ACCIDENT She walks beneath a large tree when a few leaves fall onto her hair. She stops, looks confused, then realizes what happened and laughs. — QUIET MOMENT She reaches a low concrete wall beside the street and sits down for a moment. — FINAL MOMENT She stands up and continues walking home.
Seedance 2.5@AIwithkhan345 wordsOpen case →
Template · Frozen Time and Rewind in a 1950s DinerQuoted verbatim
Photorealistic cinematic 1950s American diner, chrome stools, red vinyl, neon glow and checkerboard floor, shot with modern lived-in realism and soft natural window light. Subtle handheld texture, warm practicals, rich period detail, heavy film grain.

0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at the counter, calm and slightly amused, slowly sipping a tall thick milkshake through a straw. Behind her a young waitress in classic uniform approaches with a tray of eggs and bacon in one hand and a full glass coffee pot in the other. An older lady starts rising from a nearby booth.

4-8s: [Dynamic Tracking] The older lady collides hard into the waitress. Tray, plate, eggs, bacon and coffee pot explode upward in chaotic slow motion. Coffee erupts into long liquid ribbons and perfect suspended droplets. Camera immediately begins a smooth continuous orbit around the impact. Time locks completely at the peak of the spill. Every face freezes in pure shock. Only the girl at the counter keeps moving, completely unfazed.

8-17s: [Slow 360° Orbital] Camera glides in a full elegant orbit through the frozen diner. Coffee hangs in mid-air as glassy ribbons and spheres with perfect volume and surface tension. Bacon strips, eggs and the spinning tray float weightlessly. Patrons and waitress remain locked in startled expressions. The girl at the counter takes one slow, deliberate sip, eyes half-lidded, almost bored, while the entire frozen world (except her) begins an elegant reverse: every droplet, every piece of food and every person rewinds smoothly back to the exact starting positions.

17-24s: [Medium Shot] Rewind lands perfectly. Waitress stands balanced again with tray and coffee pot. The girl lifts her eyes, raises two fingers in a small casual gesture and softly calls the waitress by name. The waitress turns toward her just before the older lady begins to stand, completely avoiding the collision. A tiny private smile crosses the girl’s face.

24-30s: [Extreme Close-Up] Hard cut to her face as she takes one last slow sip. Soft knowing smile, eyes almost closed in quiet satisfaction, like she has done this a hundred times. Shallow depth of field, creamy bokeh of the neon diner behind her.

Photorealistic, ultra-detailed fluid physics, perfect motion blur only on moving elements, stable characters, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence, high rewatch value.
Seedance 2.5@techhalla390 wordsOpen case →

04Sources

Official Sources

05Related topics

Related topics

06FAQ

Frequently Asked Questions

How long can Seedance 2.5 generate in one pass?

Seedance 2.5 jointly generates audio and video for up to 30 seconds per generation in a single pass, up from 15 seconds in Seedance 2.0. It also supports multi-round extension.

What references and editing controls does it support?

One pass can use up to 30 images, 10 video clips and 10 audio clips. Supported references include clay renders, motion and creative references. Editing supports timestamps, green screen, camera perspective and reference-based changes.

When was Seedance 2.5 launched, and where is it available?

ByteDance Seed launched Seedance 2.5 on July 31, 2026. It rolled out on Jimeng AI and Doubao Pro. The launch post points to BytePlus ModelArk for API access.