剑挥君 retweeted
Created with GPT image 2
Prompt:
Ultra-realistic night portrait of a beautiful young woman standing on a balcony overlooking a city skyline, wearing an elegant sleeveless cream plaid dress, soft blush makeup, natural glossy lips, and a relaxed half-up hairstyle with loose face-framing strands. Looking back over her shoulder toward the camera with a gentle expression, warm flash photography illuminating her face against a dark night sky. City lights and apartment windows glowing softly in the background, cinematic urban atmosphere, high contrast lighting, shallow depth of field, dreamy bokeh, realistic skin texture, detailed eyes, fashion editorial photography, luxury lifestyle aesthetic, DSLR quality, 85mm lens, f/1.8, photorealistic, ultra-detailed, soft color grading, masterpiece, 8k.
Negative Prompt:
blurry, low quality, pixelated, overexposed, underexposed, bad anatomy, extra fingers, distorted hands, duplicate person, unrealistic face, plastic skin, cartoon, anime, CGI, watermark, text, logo, noise, grain, motion blur, harsh shadows, oversaturated colors, cropped body, poor composition, deformed features.
剑挥君 retweeted
🤯 Depth videos perfectly solve false flags on reference videos — and can perfectly recreate both martial arts and dance!
Turned a Guan Dao martial arts clip into a Depth motion reference, swapped the fighter for a market auntie, and moved the scene to a T-junction inside a local market 🤣
🌟 Workflow:
1. Pick a reference clip under 15 seconds
2. Convert it to Depth with Depth Anything V2
3. Generate a new character + scene
4. Feed everything into Seedance with the prompt below
🌟 Depth video conversion:
You can build a local Depth converter with Codex — prompt in the comments.
This goes way beyond trending dances.
Martial arts, polearms, and other complex movements can all be transferred cleanly with Depth!
Workflow + Prompt below 👇
🤯热门视频避免误审或卡脸,先转成 Depth 保留动作,AI完美复刻!
推友 @impalementd 分享了一个好方法:
把参考视频转成 Depth,可以避免原视频因画面问题被卡!
抖音热门的“拖拉机舞”,被我换成机能辣妹在田边跳,引来村狗围观🤣
🌟制作流程:
1. 准备一段你喜欢的视频(比如舞蹈)
2. 使用深度估计模型gradio转换Depth视频
3. 生成新的角色+场景参考图
4. 参考评论区提示词 + 素材 给Seedance生成新视频
这套方式适合做更干净的动作迁移!
动作可以参考,角色、服装、场景和叙事则重新创作,最后做出来就是一个全新的版本。
Workflow + Prompt below 👇
剑挥君 retweeted
Created with GPT image 2
Prompt
Ultra-realistic smartphone selfie that genuinely looks like it was casually captured with a modern flagship phone, not a DSLR or AI render. A beautiful young Japanese woman with smooth fair skin, expressive brown eyes, glossy pink lips, and long silky dark brown hair flowing naturally. She is wearing a red Spain national football jersey (number 10), blue jeans, white sneakers, a thin gold necklace, and a small black crossbody bag.
She is sitting in the stadium stands during a FIFA World Cup match, smiling with one eye playfully closed (wink). One arm is fully extended holding the phone for a front-camera selfie, while the other arm is raised high holding a large red-and-yellow Spain supporter scarf above her head. A small Spanish flag face paint is visible on her cheek.
Behind her is a massive football stadium packed with thousands of Spain supporters wearing red jerseys, waving Spanish flags, cheering enthusiastically. A vibrant green football pitch, players in action, giant LED scoreboards, FIFA branding, bright stadium floodlights, confetti floating through the air, and an electric World Cup atmosphere fill the background.
The image is framed from a slightly high ultra-wide front-camera angle, naturally including her face, upper body, raised scarf, nearby fans, and a wide view of the stadium. Warm realistic stadium lighting, authentic smartphone HDR, subtle sensor noise, natural skin texture, slight front-camera lens distortion, mild handheld imperfections, realistic colors, computational photography, candid social media aesthetic.
No DSLR look, no cinematic lighting, no professional photoshoot, no excessive sharpness, no artificial beauty filters, no unrealistic bokeh, no AI-generated appearance.
Style: Ultra-photorealistic, authentic smartphone selfie, candid mobile photography, FIFA World Cup fan moment, Spain supporter, realistic lighting, social media aesthetic.
Aspect Ratio: 3:4
Negative Prompt:
DSLR, studio lighting, professional photography, CGI, 3D render, anime, cartoon, painting, unrealistic skin, plastic face, heavy makeup, beauty filter, fake bokeh, oversaturated colors, blurry face, low quality, watermark, text, logo, extra fingers, extra arms, deformed hands, duplicate person, cropped face, motion blur, overprocessed image
剑挥君 retweeted
Created with GPT image 2.0 on ChatGPT
Prompt: Ultra-realistic lifestyle portrait of a beautiful young East Asian woman captured from a dramatic low-angle handheld selfie perspective beneath a vivid cobalt-blue summer sky filled with soft white clouds. She smiles warmly at the camera with a gentle, natural expression, creating a fresh and inviting atmosphere. Her long, silky jet-black hair flows gracefully in the breeze, with delicate wisps framing her face and catching the sunlight. She wears a loose pastel sky-blue cottagecore blouse with short puff sleeves, a subtle lace-up neckline, and a soft, airy fabric that moves naturally in the wind. A cream-white lace headscarf tied behind her head adds a romantic vintage touch.
She has luminous porcelain-fair skin with a healthy natural glow, soft peach blush, lightly defined eyes, long lashes, naturally groomed brows, and glossy rosy-pink lips. Tiny pearl stud earrings add an elegant minimalist detail.
The composition is framed beneath a lush green tree canopy with vibrant sunlit leaves filling the upper-right portion of the frame, while expansive blue sky occupies the remaining background, creating strong negative space. Warm golden sunlight filters through the leaves, producing natural backlighting, glowing rim light around her hair, subtle lens flare, and realistic sun rays. The image has rich contrast, vibrant yet natural colors, crisp facial details, and soft cinematic depth.
Captured with a premium smartphone camera using a 24–26mm equivalent wide-angle lens, HDR photography, f/1.8 aperture, ISO 50, 1/2000s shutter speed, ultra-high dynamic range, realistic skin texture, lifelike lighting, premium color grading, photorealistic detail, Instagram-worthy composition, dreamy summer aesthetic, peaceful outdoor atmosphere, stop-scrolling social media quality, 8K ultra-realistic photography, aspect ratio 3:4.
剑挥君 retweeted
Sunday routine in Korea
GPT and Seedance thing
Prompt :
Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, soft natural makeup, skin tone, facial proportions, and overall appearance consistently throughout every scene. Maintain perfect face consistency and realistic hand anatomy. She wears a fitted white ribbed crop top with light blue high-waisted jeans throughout the video.
Create a 10-second cinematic lifestyle vlog capturing the feeling of a peaceful slow Sunday morning. Bright modern apartment with floor-to-ceiling windows, warm golden morning sunlight, cozy Scandinavian décor, soft neutral color palette, realistic handheld camera movement, premium lifestyle aesthetic, photorealistic 4K HDR.
The video opens with her slowly waking up in bed as warm sunlight fills the room. She stretches naturally, smiles softly, and walks barefoot to the large window before gently opening the curtains.
She heads to the kitchen and carefully prepares a fresh pour-over coffee. Steam rises from the mug as sunlight creates beautiful highlights across the countertop. She takes a slow sip while looking out the window, enjoying the peaceful morning.
Next, she completes a relaxing skincare routine using cleanser, toner, serum, moisturizer, and lip balm. Cinematic close-ups capture glowing skin and natural reflections in the bathroom mirror.
She blow-dries her hair into soft loose waves before applying minimal everyday makeup with blush, mascara, and a glossy nude lip tint.
She opens her wardrobe, slips on her favorite light blue jeans, picks up a cream canvas tote bag, and checks her outfit in a full-length mirror with a satisfied smile.
She curls up beside the sunny window with a book and coffee, peacefully reading as sunlight falls across the pages and indoor plants gently sway nearby.
Finally, she steps outside for a quiet Sunday morning walk through tree-lined streets, smiling softly as she enjoys the calm atmosphere. The camera follows from behind before slowly moving around to capture her walking confidently toward the lens as the video fades out.
Style: Slow living aesthetic, cozy Sunday lifestyle vlog, realistic GRWM content, cinematic handheld and gimbal camera movement, authentic social media creator style, soft natural lighting, elegant transitions, shallow depth of field, photorealistic, premium lifestyle cinematography, luxury Instagram Reel aesthetic, 4K HDR, 24fps, 16:9 widescreen.
Negative Prompt: No text, no subtitles, no logos, no watermarks, no duplicate people, no AI artifacts, no distorted anatomy, no extra fingers, no exaggerated makeup, no cartoon style, no oversaturated colors, no flickering, no unrealistic facial expressions.
剑挥君 retweeted
GPT image 2 in chatgpt
Prompt:
Ultra-realistic smartphone selfie, genuinely looks like it was casually captured with a mobile phone, not a DSLR or AI render. A beautiful young East Asian woman with very fair porcelain skin, a delicate V-shaped face, soft almond-shaped brown eyes, subtle Korean makeup with natural pink lips, light eyeliner, and a short shoulder-length pastel pink bob haircut with airy wispy bangs framing her face.
She is sitting comfortably on a neatly made bed inside a cozy minimalist bedroom with warm cream-colored walls. The background features a small aesthetic collage of pastel art prints and floral posters, creating a soft Korean-inspired room decor. She wears a cute white knit sweater with pink ribbed collar and sleeve cuffs featuring a vintage cartoon kitten graphic, giving a cozy, feminine, and youthful aesthetic.
She leans slightly toward the camera with both arms naturally extended as if holding the phone herself, wearing a gentle smile with one eye slightly squinting in a playful expression. The framing is a close upper-body selfie from a slightly high handheld angle. Soft natural daylight enters through a nearby window, producing flattering diffused lighting and realistic skin tones.
The image includes subtle smartphone HDR processing, slight sensor noise, natural skin texture, mild edge softness, realistic indoor exposure, authentic white balance, and a tiny amount of handheld imperfection. No professional lighting, no studio setup, no AI-perfect sharpness, no excessive beauty filter, and no exaggerated bokeh. It should feel spontaneous, cozy, and exactly like a real flagship smartphone front-camera selfie posted on social media.
Aspect Ratio: 3:4
Style: Ultra-photorealistic, natural smartphone selfie, candid indoor portrait, Korean aesthetic, cozy bedroom, authentic mobile camera quality, realistic lighting, high detail.
剑挥君 retweeted
🤯 K-pop meets a full-on water obstacle challenge! 🌊
Made with Seedance in a Korean variety show style
Full workflow:
1. 4:3 character sheet for the girl, swimsuit and expressions
2. 3:1 wide course image for the pool set, audience and obstacles
3. Seedance image-to-video for the full run and final splash
From the confident start to the final fall, the character and scene consistency held up really well!
Workflow + Prompt in the comments 👇
剑挥君 retweeted
[Grok Prompt]
Photorealistic selfie of a cute young East Asian woman in her early 20s, shoulder-length dark brown-black hair with straight bangs and slight waves, wearing thick black rectangular glasses. She makes a playful silly face: mouth open, tongue sticking out to the side, looking straight at the camera.
She is wearing a white Tottenham Hotspur football jersey with navy blue raglan shoulders and sleeves. Prominent on the chest: the classic Tottenham cockerel crest standing on a ball, black Nike swoosh underneath, and large bold red "AIA" sponsor text below. Partial "KIA" text visible on the left sleeve.
She is sitting in a black office chair in a casual indoor room with light walls, white horizontal blinds on the left, wooden floor, and another football jersey hanging on the wall behind her. Natural daylight, realistic skin texture, sharp details, casual selfie angle, high resolution, 8k photorealism.
Add --ar 2:3 or --ar 3:4 (portrait ratio) if using Midjourney.
For Grok Imagine, just paste it as-is. @SpursOfficial
🤖 Made with AI
剑挥君 retweeted
Haircut of a Japanese girl
GPT Image 2 and Seedance
Prompt :
Create an ultra-realistic cinematic lifestyle video featuring the same young East Asian woman throughout the entire sequence. Maintain identical facial features, long soft ash-brown wavy hair, glowing skin, body proportions, and outfit in every shot. She wears a fitted white ribbed crop top, a flowing red pleated skirt, white sneakers, and carries a cream canvas shoulder bag. Bright summer morning, modern Japanese neighborhood, premium hair salon with warm lighting, realistic reflections, elegant interiors, and a relaxed lifestyle aesthetic.
The video opens with her checking herself in the bedroom mirror before lightly styling her hair. She smiles naturally, picks up her cream tote bag, grabs her phone and keys, and leaves the apartment.
She walks through a peaceful Korean street lined with cafés, flower planters, and boutique stores. The camera follows her with smooth handheld tracking as sunlight filters through the trees and a gentle breeze moves her hair.
She arrives at a stylish Japanese salon, warmly greeting the receptionist before browsing a hairstyle lookbook with the stylist. They chat, laugh, and agree on a soft layered haircut.
She relaxes in the shampoo chair while her hair is gently washed and massaged. Close-up shots capture flowing water, shampoo bubbles, warm lighting, and her peaceful expression.
The stylist carefully trims her hair, blow-dries it with smooth cinematic movements, and finishes with soft curls and a healthy glossy shine. She smiles while watching the transformation in the mirror.
After the haircut, she admires the final look from different angles, takes a quick mirror selfie, thanks the stylist with a warm smile, and leaves the salon feeling confident.
Outside, she walks through the sunny streets with her refreshed hairstyle flowing naturally in the breeze. She stops at a café window, catches her reflection, smiles happily, then looks toward the camera and gives a small friendly wave as the camera slowly pulls back to reveal the vibrant Japanese street.
Natural ambient audio only: footsteps, city ambience, café chatter, salon conversations, scissors cutting hair, hairdryer, running water, shampoo bubbles, hairbrush sounds, door chimes, birds, gentle breeze, distant traffic. No background music, no subtitles, no logos, no watermarks, and no on-screen text. Premium commercial-quality cinematography, smooth handheld and gimbal camera movement, realistic skin texture, detailed hair physics, natural expressions, physically accurate lighting, shallow depth of field, warm golden atmosphere, 16:9 widescreen, 4K HDR.
剑挥君 retweeted
⚔️ Didn’t expect Lady Gongsun’s Sword Dance to feel this powerful!
Made with ChatGPT-Image2 + Seedance.
A rain-washed Tang courtyard, warm lantern light, flowing red-black robes, sharp sword arcs, and fast turns through the night.
Used a 16-panel storyboard to shape the choreography,
and a character sheet to keep the dancer consistent.
I really like the balance between elegance and strength in this one.
Workflow + prompts in the comments 👇
🤖 Made with AI
🌧️ Didn’t expect water sleeves to look this alive in the rain!
Storyboard + character sheet with ChatGPT-Image2, seedance for the final video.
Jiangnan night rain, wet stone roads, soft lantern light, water splashes, and long sleeves moving through the air.
Used a 16-panel storyboard for the choreography,
and a character sheet to avoid the generic-face drift.
The sleeve motion through the rain is the part I like most.
Workflow + prompts in the comments 👇
剑挥君 retweeted
Graceful moves flying hair and perfect laser dodges
Made with seedance 2.0
Prompt:
A highly dynamic cinematic action sequence of a beautiful young East Asian woman with long wavy silver-gray hair, wearing a stylish dark navy blue Japanese school uniform blazer with gold buttons, white collared shirt, striped tie, gray sweater vest, short pleated navy skirt, black knee-high socks, and shiny black loafers. She is performing intense parkour and acrobatic flips, jumps, and dodges through a futuristic high-tech sci-fi corridor with metallic walls, large pipes on the ceiling, reflective dark floors, glowing white ceiling lights, and multiple glowing red laser security beams crisscrossing at different heights.
Key action moments: mid-air flips and spins while dodging red lasers, jumping over railings, balancing on metal handrails, low crouching slides, dramatic leaps, and landing in front of a massive heavy vault door with mechanical locks. Close-up intense facial expressions (focused, determined).
Atmosphere: dramatic lighting with strong red laser glows reflecting on surfaces, cool blue-white ambient lights, cinematic camera angles (low angle, tracking shots, Dutch angles), motion blur on fast movements, hair flowing dramatically. Ultra-realistic, photorealistic, 8K detail, high-speed action style like a Hollywood sci-fi movie trailer.
剑挥君 retweeted
GPT image 2 in chatgpt
Prompt:
Ultra-realistic smartphone photo, genuinely looks like it was casually captured with a mobile phone, not a DSLR or AI render. A beautiful young East Asian woman with very fair porcelain skin, a delicate V-shaped face, large soft brown eyes, subtle Korean makeup with light pink lips, and long silky platinum silver hair with full straight bangs flowing naturally over her shoulders.
She is standing on a quiet urban street at night outside a modern café and commercial building with glowing neon storefront signs, glass windows, black barriers, yellow-and-black safety tape, and softly blurred city lights in the background. She wears an oversized black, gray, and white plaid knit poncho layered over a crisp white collared shirt with loose sleeves, creating a cozy Korean street-fashion aesthetic.
She faces the camera directly with a calm, slightly shy expression, shoulders relaxed, hands naturally out of frame. The image is framed from the waist up with a slightly high handheld angle, as if a friend quickly took the picture using a smartphone. Soft ambient streetlights and nearby shop lighting illuminate her face naturally, with realistic skin texture, slight mobile-camera noise, gentle HDR processing, subtle motion softness, authentic night exposure, shallow computational depth of field, and natural color balance.
No professional lighting, no studio setup, no overly sharp AI look, no beauty filter, no exaggerated bokeh. The composition feels spontaneous, candid, and effortlessly aesthetic, exactly like a real flagship smartphone night-mode photo shared on social media.
Aspect Ratio: 3:4
Style: Ultra-photorealistic, natural mobile photography, candid street portrait, Korean aesthetic, authentic smartphone camera, high detail, realistic night lighting.
The Thunder Warrior
Made by Seedance 2 on @higgsfield
Video Prompt:
One continuous unbroken take, no cuts: the camera starts low behind the white-haired armored warrior, her cyan-veined suit glowing faintly as she faces a ruined torii gate with a white tiger prowling beside her and a horde of gray zombies filling the shattered street beyond. The lens begins a slow push forward past her shoulder, then whips into a fast low orbit around her right side as she launches upward, the camera tilting and rising with her leap, chasing her axe as it trails a ribbon of electric blue light through the air. As she crashes down onto the horde, the camera dives with her, snapping into a violent handheld shake at ground level, lightning bursts erupting outward as the axe connects, the white tiger lunging into frame past the lens. Without cutting, the camera rockets straight upward into a vertigo-inducing aerial pull-back, spiraling higher and higher until the entire ruined city and the swarming crowd below become a churning sea of bodies split by a jagged vein of electric light — then the camera plunges back down in a swooping vertical dive, hurtling toward the fight and snapping into extreme close-up as her glowing gauntlet grips a zombie's face, sparks scattering across the lens. The camera swings around her in a tight 180-degree arc, revealing a clawed beast lunging from the far side; she pivots her axe defensively, and the camera whip-pans with the motion, dust and debris flying past frame. It then drifts backward and rises into a wide crane shot as she plants her weapon into the ground beneath a churning storm-lit sky, chains of energy crawling up her arms — the camera slowly rotates around her rising silhouette. Suddenly the light detonates outward and the camera is thrown backward as if caught in the blast, shuddering and rolling through the shockwave, streaks of lightning tearing across the frame as bodies are hurled aside. Finally, the camera stabilizes and glides backward in a slow, steady pull, rising just slightly to frame her standing alone amid the wreckage and fallen torii gate, hair and cloak settling in the wind, the devastated skyline stretching behind her as the single take comes to rest., Mandatory: never show the storyboard ref in the video
🤝 Paid partnership · 🤖 Made with AI
剑挥君 retweeted
Seedance 2.0 in @Flovaai
Prompt:
Stylish idol dressing room at an MV filming studio, midday. A cheerful Korean female idol (@ image) films a fun, high-energy behind-the-scenes "Idol Swap Challenge" vlog entirely on her phone using dynamic handheld selfie shots, smooth mirror angles, and fast-paced cinematic editing. She smiles brightly at the camera and says, "Let's see how many styles I can become today!" With a playful snap of her fingers, she instantly transforms into a cute look, making adorable finger hearts and sweet expressions. Another snap transitions her into a cool concept with a confident attitude, sharp eye contact, and stylish poses. She spins once, seamlessly changing into an elegant look, gracefully adjusting her hair and smiling softly in front of the vanity mirror. With one final playful spin, she transforms into a funny version of herself, making exaggerated facial expressions, pretending to model dramatically, and bursting into genuine laughter. Each transformation is smooth and magical, with lighting, poses, and expressions changing instantly while remaining in the same dressing room. The vlog ends with her returning to her original look, pointing at the camera with a bright smile and asking, "Which version is your favorite?" She makes a finger heart, waves goodbye, grabs her phone, and happily heads out for filming, ending the video with energetic, playful, and viral-worthy idol vibes.
🤝 Paid partnership
剑挥君 retweeted
Seedance 2.0 on Higgsfield AI
Full open-sourced prompts & assets below:
SCENE CONTEXT
A young woman sleeps on her side in her pink bedroom at night; in a single locked frame the room snaps instantly from night to morning like a finger-snap time jump. She sleepily half-wakes, turns over to find a white cat curled against her back, then pushes up to half-sitting and sees her room quietly tidied — her school uniform hung on the chair and her backpack packed on the vanity.
ACTIVE REFERENCES
<<<image_1>>>: young woman, low pigtails, pink hair-roller clip, beige t-shirt with brown long sleeves, sleeping then waking. 100% matches the reference.
<<<image_3>>>: fluffy white long-haired cat, adult, curled and pressed against her back. 100% matches the reference.
<<<image_2>>>: pink bedroom. 100% matches the reference. Every element and corner is preserved and stays consistent across all shots.
<<<image_4>>>: school uniform — navy cardigan, white shirt, green-striped tie, plaid skirt, knee socks — draped and hung on the pink chair. 100% matches the reference.
<<<image_5>>>: solid pink backpack with front zip pocket and pink pompom keychain, packed and zipped, standing on the vanity table. 100% matches the reference.
LOCATION MAP
Pink bedroom, remembered corner by corner and held identical in every shot:
- Screen-left: a wooden door with a brass knob, dark wood trim and wood wainscoting along the lower wall, blush-pink upper walls.
- Beside the door: a large ornate pink-and-white Victorian dollhouse with a small pink chair at its base.
- A white vanity desk with a trifold arched mirror, cluttered with cosmetics, brushes and small bottles, a pink desk chair tucked at it.
- A wide window with sheer white curtains behind the vanity; a leafy potted plant beside it.
- A tall brass floor lamp standing near the bed.
- A wooden nightstand at the head of the bed with a small lamp, a framed photo, a tissue box and a cup.
- The bed against the wall: carved wooden headboard, pink ruffled bedding, pink pillows, a soft pink blanket — the central anchor of the room.
- A woven area rug over dark hardwood floor, a small wall shelf with items above the bed side.
FIRST FRAME AND SPATIAL BLOCKING
The first visible frame is a close-up of her sleeping face. She lies on her left side facing the bedside lamp / nightstand side, cheek on the pink pillow, hair loose, pink hair-roller clip visible, breathing slow. The bed's pink blanket is clean and clear. No empty establishing frame.
FORMAT MODE
Controlled four-shot sequence with HARD CUTs at 4.0s, 8.0s and 11.5s. The night-to-morning transition inside shot 1 is an instantaneous in-frame light change, not a cut. Real-time motion. No subtitles, no music.
OPTICS
Shot 1: 50° diagonal field of view, standard normal lens character, camera 0.6 to 0.8 meters from her face, shallow depth of field — closed eyelids, lashes, loose strands and the hair-roller clip razor-sharp, the room soft behind.
Shot 2: 56° diagonal field of view, near-normal lens character, camera 1 meter, holding her face and the white cat against her back, rack focus available between them.
Shot 3: 63° diagonal field of view, slightly-wide lens character, camera 1.5 to 2 meters, rising with her as she sits up, more of the room entering frame.
Shot 4: 84° diagonal field of view, classic wide lens character, camera 2 meters, wide enough to reveal the tidied room — vanity, chair and bed together — then easing toward her.
CAMERA
Shot 1: locked close-up with a very slow creeping push-in; the framing does not change through the night-to-morning snap.
Shot 2: small reframe and rack focus as she turns, pulling focus onto the cat curled at her back, then back to her reacting face.
Shot 3: a smooth crane-up rising with her from lying to half-sitting, revealing the room behind the bed.
Shot 4: a slow pan across the tidied room — uniform on the chair, packed backpack on the vanity — settling with a gentle push-in on her half-sitting figure and dawning expression.
ACTION TIMING
0.0s to 2.0s: close on her sleeping face at night, perfectly still, breathing slow, cool dim room around her.
2.0s: an instantaneous in-frame light snap — the room flips from night to morning in a single frame, no cut, no dissolve; she does not move at all, only the light changes, like a finger-snap time jump.
2.0s to 4.0s: hold on her face now in soft warm morning light, still asleep for a beat.
4.0s HARD CUT.
4.0s to 8.0s: she sleepily half-opens her eyes, stirs, and turns over toward screen-right, discovering a fluffy white cat curled warmly against her back; her half-lidded eyes drift to it.
8.0s HARD CUT.
8.0s to 11.5s: she pushes herself up on one arm to half-sitting, hair mussed from sleep, blinking and groggy, beginning to glance around the room.
11.5s HARD CUT.
11.5s to 15.0s: reveal of the quietly tidied room — her navy cardigan and plaid skirt uniform hung neatly on the pink chair at the vanity, the packed pink backpack standing zipped on the vanity table, its pompom keychain still — her expression softening into slow, disbelieving realization as she takes it in.
PHYSICS
During the night-to-morning snap her body is absolutely motionless — only light changes, no drift, no shift. As she wakes, eyelids lift heavily, she rolls with natural weight and the mattress and blanket shift under her; the cat's long fur rises and falls with slow breathing and compresses softly where it presses to her back. Sitting up, her hair falls loose in individual strands, the blanket sliding down naturally, her supporting arm taking real weight.
LIGHTING
Cinematic and restrained throughout, never bright or flat. Night (pre-snap): low-key cool moonlight through the sheer curtains with a faint warm practical accent, deep but detailed shadow, moody film texture and soft grain. At the snap, the light flips instantly to soft warm directional morning sun through the sheer curtains — golden but controlled and filmic, gentle rolloff, faces readable, shadows soft, not overexposed or blown out. The warm-cool contrast and naturalistic grain carry the cinematic feel into every shot.
AUDIO
Shot 1: quiet steady sleeping breath, faint cool room tone; at the snap a soft airy shimmer-whoosh transient marks the time jump, then gentle morning birdsong and warm ambience fade in. Shot 2: a soft sleepy inhale, faint fur rustle as she finds the cat, a quiet purr. Shot 3: soft blanket rustle as she sits up. Shot 4: quiet held breath, faint ambient morning tone under her realization. No dialogue, no music, no subtitles.
POSITIVE LOCKS
Woman matches <<<image_1>>> exactly, cat matches <<<image_3>>> exactly, bedroom matches <<<image_2>>> exactly and every listed corner — wooden door, dollhouse, vanity with trifold mirror, pink chair, brass floor lamp, wooden nightstand, carved bed with pink ruffled bedding, woven rug — stays present and consistent across all four shots, with no new or missing furniture. The bed's pink blanket is clean and clear — no laptop, bag, papers or objects resting on top of it. The night-to-morning transition is one instantaneous in-frame light change on a single locked framing; she does not move during it — no dissolve, no fade, no camera cut. The white cat lies pressed against her back. In the final shot the uniform hangs on the pink chair matching <<<image_4>>> and the packed backpack sits on the vanity matching <<<image_5>>>. Lighting stays cinematic and controlled, never bright or washed out.
🤝 Paid partnership
剑挥君 retweeted
Seedance 2.0 on @Flovaai
===================
Prompt:
[Reference Identity Lock]
Image 1 is ONLY the main female protagonist.
Her face, hairstyle, body type, and outfit must match Image 1 exactly and stay consistent for the entire video.
Image 2 is ONLY a uniform reference.
All four opponents wear the school uniform shown in Image 2.
Never swap, merge, duplicate, or blend identities.
The protagonist's identity comes ONLY from Image 1.
The four opponents have NO reference images. They are defined by the text descriptions below.
The four opponents must not resemble the protagonist, and they must not resemble each other.
All five characters must remain clearly distinct and recognizable until the end.
[Priority Order]
1. Preserve the protagonist's identity from Image 1.
2. Keep the four opponents visually distinct from her and from each other.
3. Maintain one continuous shot with no cuts.
4. Keep the classroom layout spatially consistent.
5. Make the action fast but readable and physically connected.
6. Keep the tone as a Korean school action drama, stylish but grounded.
Korean school action drama classroom fight scene — 15 seconds, ONE CONTINUOUS SHOT, NO CUTS.
A single uninterrupted handheld shot.
No cuts, no scene transitions, no montage.
The camera should feel handheld, with micro-jitters, slight rolling shutter, and raw unstable realism.
The camera must physically travel through the same classroom space.
Every transition must be motivated by camera movement, not editing.
Whip pans are allowed, but they must not hide a cut.
Do not teleport the camera or characters.
The classroom layout and character positions must remain spatially consistent.
Audio:
No music.
Only realistic school and classroom ambient sounds:
old fluorescent light hum, distant hallway noise, ceiling fan, shoes scraping the floor, desks dragging, chair legs screeching, cloth friction, dull body impacts, and breathing that gradually becomes heavier.
Breathing continues throughout the scene and keeps building.
Lighting:
Late afternoon in a Korean high school classroom.
Mixed cool fluorescent light and warm sunlight through the windows.
Dust floating in the sunlight.
Soft fan shadows moving across desks and school uniforms.
Main character:
The Korean female high school student from Image 1, age 17–18.
Cold, emotionless, calm, and intimidating.
She barely speaks and does not scream during the fight.
She remains composed from beginning to end.
Her movements are efficient, explosive, and precise.
Even if her frame is not large, she dominates through speed, timing, and accuracy.
Main outfit:
Exactly the outfit shown in Image 1.
Do not change its colors, design, or details.
Her jacket or outer layer is either removed and hanging on a chair, or worn in a slightly messy way.
The action must be non-sexualized and combat-focused.
Fabric movement, dust, sweat, wrinkles, and impact response should feel realistic.
Opponent rules:
Four Korean female high school students, all wearing the Hanlim Multi Art School uniform shown in Image 2.
They have no reference images. Define them strictly by these descriptions and keep each one consistent:
Opponent A: short black bob with straight bangs, medium build, round face.
Opponent B: long straight hair tied in a high ponytail, tall and lean, sharp jawline.
Opponent C: shoulder-length hair with side-swept bangs, slim build, narrow face.
Opponent D: long wavy hair worn loose, slightly stocky and broad-shouldered.
A, B, C, and D must each keep clearly different faces, hairstyles, body shapes, and silhouettes.
They must not resemble the protagonist, and they must not resemble each other.
No face duplication, no face merging, no identity confusion.
Environment:
An empty classroom at Hanlim Multi Art School, a Korean performing arts high school in Seoul.
Green chalkboard, chalk tray, worn wooden desks, plastic chairs, classroom clock, class schedule poster, discipline/life-guidance posters, cleaning tools, blinds or curtains, wall study materials, and a slightly scuffed floor.
Desks and chairs should react naturally to impacts, sliding, shaking, and collapsing when hit.
Camera framing rules:
Even during kicks, framing should stay around chest-level or eye-level.
No low-angle shots under the skirt.
Do not focus on legs, thighs, underwear, or fetish-like details.
All action framing must prioritize faces, upper-body motion, impact, and spatial choreography.
Continuous action and camera choreography:
From 0 to 15 seconds, the fight continues without any cuts.
The action should be stylish but readable, and every movement must be physically connected.
0–3s:
The camera starts behind the protagonist at a slightly low handheld angle, drifting left through the classroom aisle.
Opponent A grabs the protagonist's shoulder roughly and says in Korean:
"야, 너 지금 뭐 하자는 거야?"
The protagonist silently turns and lands one hard straight punch to A's face.
At impact, use a very brief 15% slow motion:
cheek ripple, dust particles, deep thud.
A falls sideways into a desk.
The camera dips slightly from the shock, then whip-pans right without cutting.
3–6s:
Opponent B charges in from the right.
The protagonist steps forward instead of retreating.
A short body shot to the stomach.
Immediate uppercut to the chin.
Without pausing, she drives forward into a flying knee to B's chest.
B is thrown backward across or into a desk.
The camera follows the forward motion low, then rebounds upward with the impact.
6–9s:
Opponent D attacks with two fast punches.
The protagonist deflects both strikes with her arms, then flows into a turning backfist to D's face.
As D staggers, she continues the same rotation into a spinning back elbow that lands hard on D's jaw or temple.
D crashes sideways into two or three desks.
The camera arcs around her shoulder and jitters slightly at each impact.
No cuts.
9–12s:
Opponent C rushes in from the chalkboard side.
The protagonist clearly grabs C's collar with her left hand.
C's face must be fully visible from the front and clearly different from the protagonist.
The protagonist lands one short, hard punch to C's face, then immediately throws a powerful high kick or flying high kick into C's chest.
The force sends C backward into the green chalkboard.
The protagonist remains in the foreground and never touches the board.
The protagonist's face should be side-profile or partially obscured.
C's face should be clearly visible from the front at the moment of impact.
Their faces must never overlap in frame.
Use a very brief 20% slow motion at the chalkboard impact:
chalk dust bursts outward, and C slides down the board.
The camera pushes up with the impact, then tilts down as C slides.
12–15s:
Through the chalk dust, the camera hard-pans right.
D makes one final charge.
The protagonist sidesteps and lands a tight uppercut to D's chin, followed immediately by a cross.
D crashes into a row of desks, causing a chain reaction of collapsing desks and chairs.
The camera drifts forward slowly.
The protagonist adjusts her loose tie or ribbon and brushes chalk dust off her shoulder.
Her expression stays cold and serious.
She walks past the camera and exits the frame.
Dust floats in the sunlight.
Natural ending.
===================
Made with Flova
#FlovaAI #FlovaCPP
🤝 Paid partnership































