AI Video Creator • Tester • AI Tools Expert Partner: @makeugc
Joined March 2026
- Tweets2.6K
- Following473
- Followers5.5K
- Likes5.8K
Pinned Tweet
Made with Seedance 2.5 (native 30-second video, no editing)
Prompt: ⬇️
CAMERA:
DV 16mm tape camcorder handheld aesthetic. A gorgeous glamorous European fitness influencer films herself directly by hand in selfie-cam and first-person style. Keep realistic hand shake, slightly crooked framing, delayed autofocus, awkward zoom-ins and zoom-outs, occasional motion blur, and small framing mistakes where part of her face briefly slips out of frame. Mix handheld selfie footage with a few fixed external shots. Important: never show her placing, adjusting, or setting up a camera. When switching from handheld footage to a fixed external angle, use a clean jump cut as if the camera had already been positioned before the shot began. The camera itself must never appear on screen.
LOOK:
Soft digital tape camcorder look with subtle vintage DV character. Slight blur, faint tape noise, mild highlight bloom under gym lighting, subtle auto-exposure flicker, muted contrast, realistic skin texture, believable indoor lighting, realistic skin tones.
STYLE:
A realistic late-night gym vlog with a sexy Instagram-model vibe. The tone is playful, confident, a little flirty, slightly breathless, and natural. She is clearly attractive and charismatic, but the video should still feel like a believable self-recorded vlog, not a polished commercial. Fast clean jump cuts, strong continuity, natural body language, no awkward dead moments.
CHARACTER:
An exceptionally beautiful glamorous European brunette woman in her mid-20s. She has a highly photogenic face, large almond-shaped brown eyes, long lashes, full glossy lips, sculpted cheekbones, a refined nose, flawless lightly tanned glowing skin, and long thick glossy dark-brown hair tied in a high ponytail. She looks like a high-end Instagram fitness and lifestyle influencer, not an ordinary gym visitor. She has a slim, feminine, athletic hourglass figure. She wears polished soft-glam makeup, a fitted stylish long-sleeve athletic crop top, high-waisted fitted leggings, clean white sneakers, and a towel around her neck or over one shoulder. No jewelry.
SETTING:
A quiet modern gym late at night. Mirror wall, dumbbell rack, flat bench, stretching mat, a water bottle on a bench, soft warm overhead lights, mostly empty space, calm atmosphere, no crowd, no trainer, no extra people.
IMPORTANT CONTINUITY RULES:
The same woman must remain fully consistent in every shot. No face changes, no hairstyle changes, no outfit changes, no body changes. No extra people appearing. No duplicated limbs. No broken hands. No disappearing water bottle. No broken gym equipment. No impossible movements. No camera visible. No camera setup shown. Keep her beautiful, polished, and photogenic in every shot.
STORYBOARD (30 seconds total, 10 cuts):
1. (~3s, arm’s-length selfie)
She walks slowly through the gym holding the camera herself, slightly out of breath but smiling confidently.
Dialogue: “Okay… late-night gym vlog.”
2. (~3s, handheld pan across the room and back to her)
The camera drifts across the dumbbell rack, mirror wall, and empty gym floor, then returns to her face.
Dialogue: “It’s basically empty in here.”
3. (~3s, mirror selfie angle)
She stops near the mirror, adjusts her ponytail, glances at herself, then smirks at the lens.
Dialogue: “I look tired, but we’re still doing this.”
4. (~3s, fixed external medium shot)
Jump cut to a fixed shot. She is already in position near the bench, picks up a pair of dumbbells, and gets ready. No camera setup shown. No dialogue.
5. (~3s, same fixed shot)
She performs a short controlled set of dumbbell shoulder presses or dumbbell chest presses with clean form, then lowers the weights and exhales with a smile.
Dialogue: “That woke me up fast.”
6. (~3s, handheld walking selfie)
She picks the vlog back up in selfie mode, towel over one shoulder, breathing a little harder as she walks a few steps.
Dialogue: “Upper body done… and I’m already dying.”
7. (~3s, tight handheld close-up)
She grabs the water bottle, takes a drink, lowers it, and exhales in relief.
Dialogue: “Best part of the workout.”
8. (~3s, fixed external wider shot facing the mirror)
Jump cut to a fixed shot. She does a quick playful stretch, a small mirror pose, then laughs softly at herself.
Dialogue: “A little stretch so I can pretend I’m disciplined.”
9. (~3s, handheld close selfie)
Her cheeks are slightly flushed, she brushes back a loose strand of hair, smiling in a tired but satisfied way.
Dialogue: “I always say quick workout… and then stay forever.”
10. (~3s, arm’s-length selfie ending)
She walks toward the exit, still filming herself, gives a tired little wave and a genuine smile.
Dialogue: “Okay, I’m done. Good night.”
FINAL INSTRUCTION:
The result must feel like a real self-recorded late-night gym vlog by a glamorous Instagram fitness influencer. Prioritize realistic handheld motion, strong continuity, believable pacing, natural breathing, attractive appearance, and subtle imperfection. Keep it sexy, polished, and realistic — not artificial, not stiff, not boring.
#AIVideo
🤖 Made with AI
Made with Seedance on @atlas_cloud_ai
Prompt: ⬇️
CAMERA:
Handheld DV 16mm camcorder aesthetic, first-person / selfie POV. MILA always holds the camera herself. Keep natural hand shake, slightly messy framing, delayed autofocus, awkward zoom-ins and zoom-outs, and occasional moments where part of her face gets cropped. The camcorder itself is never visible on screen.
LOOK:
Soft vintage DV tape quality with slight blur, subtle tape noise, gently bloomed highlights, mild auto-exposure flicker, low contrast, and realistic skin tones.
STYLE:
Bright, playful backstage vlog energy with a polished pop-star feel. Natural smiles, direct eye contact, candid excitement, and quick handheld moments that feel spontaneous and fun.
CHARACTER:
MILA — a beautiful Instagram-style brunette model and performer in her 20s. Long dark brown hair, glowing skin, attractive feminine features, glossy lips, expressive eyes, slim fit figure. Wearing a stylish stage outfit with soft glam makeup and delicate sparkly earrings.
SETTING:
Backstage hallway of a music show venue, with dressing room doors, MILA’s name tag on one of the doors, a snack table, overhead PA speaker, and blurred staff occasionally moving through the background.
SEQUENCE:
1. Selfie: she peeks into the hallway with a grin.
“Hi guys, I’m backstage right now.”
2. Quick pan down the corridor.
“This place seriously goes on forever.”
3. She stops at her dressing room and points to the name tag.
“That’s my room.”
4. Close-up of the name tag as she taps it.
Ambient backstage audio only.
5. Quick outfit check near a mirror with a playful little turn.
“Okay... stage look check.”
6. At the snack table, she grabs a small snack.
“Just grabbing a tiny pre-show snack.”
7. Mid-bite, the PA announcement cuts in. She laughs.
“Oh wow—right on time.”
8. Selfie ending: she hears the countdown, gives a wave and a finger-heart, then hurries toward the stage.
“That’s my cue — see you after the show!”
#AIVideo
Alpha Mom retweeted
I need this at work
Made with Seedance 2.5 on @makeugc
PROMPT ⬇️
Create a 15-second photorealistic live-action office comedy, landscape 16:9. MILA activates a fold-out privacy canopy over her workstation and settles down for a nap. The absurd invention is presented with the everyday realism of an ordinary office recording.
CHARACTER
MILA — a beautiful American Instagram-style brunette model and performer, 20. Long dark-brown hair in a high ponytail, natural skin texture, glossy lips, expressive eyes, soft glam makeup and delicate sparkly stud earrings. Slim athletic figure with a very large, full bust, very full rounded buttocks, a narrow waist, flat stomach, lean arms and slender legs.
She wears an open, fitted navy blazer over a cream scoop-neck top showing cleavage, a matching short navy pencil skirt and black closed-toe heels. The clothes have ordinary fabric texture, seams and natural creases. A soft grey travel pillow supports her neck. Her appearance and outfit remain consistent throughout.
SETTING
An ordinary American open-plan office during working hours. Low grey fabric cubicle partitions, off-white desks and drawer units, black monitors, folders, pens, desk phones, a few plants and grey carpet. A low white acoustic-tile ceiling has rows of long rectangular fluorescent-style light fixtures.
MILA sits in a black wheeled office chair at a desk with an open laptop. A folded grey fabric canopy and its curved support ribs are already visibly attached to her workstation. A round activation button is mounted on the partition within easy reach.
There are THREE clearly separated tent-equipped workstations: MILA's in the foreground, another behind her on the left, and a third behind her on the right. Leave enough space between them for the final camera angle to show all three enclosures.
All three use the same rounded, dome-shaped retractable tent. Bowed support ribs form a vaulted roof and curved side walls, with grey fabric extending almost to the carpet. The completed enclosure has real depth and surrounds the entire desk and reclined chair. Its small clear window is part of the curved fabric wall at the seated occupant's head height.
The folded ribs and attached fabric already exist before activation. The same structure unfolds into the dome; it does not change into a different device. No flat hanging curtains, rectangular fabric boxes or roller blinds.
Several adult coworkers in normal American office clothes quietly continue their work.
CAMERA
DV 16mm tape camcorder handheld feel.
A coworker films MILA from the aisle, with restrained handheld movement and ordinary observational framing. The camera and operator never appear.
Use a moderately wide perspective and an oblique three-quarter angle that shows the depth of the desk and tent. Substantial depth of field: nearby partitions, folders, ceiling fixtures and background coworkers remain legible. Avoid a symmetrical front-on product-demonstration composition or portrait-style background blur.
Subtle hand movement and small framing adjustments. No floating camera, cinematic orbit or dramatic push-in.
Exactly three shots, with cuts only at 2.5s and 8.5s. Each tent deployment is shown continuously within its shot. The entire final wide shot is one uninterrupted take with no hidden cuts or time jumps.
The opening three-quarter medium shot includes MILA's face, full bust, waist, the activation button and the folded canopy. Her face is clearly readable without cropping the image into a tight face-only portrait.
LOOK AND LIGHTING — ESSENTIAL
Plain, naturally exposed office footage. Bright neutral office whites, a very slight cool fluorescent cast, restrained saturation and clear detail across both the subject and the surrounding room. Expose for the occupied office: pale desks and partitions stay bright, with readable midtones on MILA's face and navy jacket. Avoid a dim, warm, cinematic treatment.
MILA receives the same overhead illumination as the desks and coworkers around her. Broad, overlapping light from the rows of ceiling fixtures produces soft shadows beneath her brow, nose and chin. Reflected light from pale desks, walls and ceiling gently fills these shadows. Her face has no separate frontal beauty light or rim light.
Preserve ordinary facial detail at this viewing distance: subtle variation in skin color, small creases around the eyes and mouth, slight natural asymmetry and individual stray hairs. Keep her makeup as described. Her face, hands, clothes and the office share the same focus, exposure and recording texture. No isolated smooth, retouched face against a detailed background.
Keep only subtle consumer-video softness and recording texture. Faces, fabric and background desks remain readable. No heavy VHS filter, excessive blur, added haze, exaggerated grain or artificial face sharpening.
The grey canopy has lightweight woven fabric, visible stitching, uneven folds and tension around its curved supports. Maintain natural differences between cloth, skin, plastic and metal.
As the canopy closes, it progressively blocks the overhead light. Only the enclosed workstation becomes darker. A subdued warm desk light then becomes noticeable on MILA's face through the clear window. The surrounding office retains exactly the same bright neutral exposure and color. The warm light stays local, without turning her skin orange or changing the whole room.
No beauty retouching, glossy commercial grading, golden-hour sunlight, dramatic rim light or teal-and-orange treatment.
STYLE
Dry, understated workplace humor. MILA treats the device as a completely normal office convenience. Relaxed, slightly tired behavior and natural blinking. Her brief satisfied smile gently relaxes as she settles into the pillow. Her jaw and lips relax before she closes her eyes; she does not maintain a fixed model's smile while sleeping. Small natural breathing movements continue.
Coworkers do not perform exaggerated reactions.
STORYBOARD — 15 SECONDS
0.0–2.5s — THE BUTTON
Begin directly on MILA already seated with the neck pillow in place. The folded canopy is visible above the partition.
She reaches out, presses the round button once, withdraws her hand and eases back into the chair. Her head settles into the pillow. The canopy begins moving immediately after the press.
2.5–8.5s — THE WORKSTATION CLOSES
Cut to a wider three-quarter view showing the desk, chair and entire moving canopy.
Hold this shot continuously throughout the complete deployment.
The leading curved hoop rises from the folded assembly, sweeps upward and forward over MILA's head, then travels downward outside the chair. The other bowed ribs spread behind it, drawing the attached fabric into a rounded, three-dimensional dome.
Show the entire structure, including the roof, curved side walls and descending lower edge. The fabric stays attached to its supports. Folds stretch out progressively; loose edges sway slightly and settle. The frame clears MILA, the laptop and the chair.
By 7.5s, the dome is FULLY CLOSED around the desk and reclined chair. Its lower fabric edge reaches almost to the carpet, enclosing her legs and the chair base. The small transparent window remains at face height. This is a complete rounded tent, not a rectangular curtain lowered in front of an otherwise open cubicle.
From 7.5–8.5s, hold the completed shape. MILA is visible through the window with her head supported and eyes closed. The soft warm interior light becomes noticeable on her face.
8.5–15.0s — BUSINESS AS USUAL
One uninterrupted oblique wide shot of the same office. Frame all THREE workstations together without MILA's foreground dome blocking the two behind it.
8.5–9.0s:
MILA's completed dome is in the foreground. An IDENTICAL FULLY CLOSED DOME is clearly visible behind her on the LEFT. Behind her on the RIGHT, a seated coworker in a white shirt is at the third workstation, whose identical canopy is still folded.
9.0–12.5s:
The seated coworker presses their own button and reclines. The RIGHT-HAND canopy performs the SAME COMPLETE DEPLOYMENT as MILA's: the existing curved hoop rises, sweeps over the occupied workstation and descends around the outside of the chair. The attached ribs and fabric spread into the same full rounded dome. Its lower edge reaches almost to the carpet. Finish the entire movement by 12.5s.
12.5–15.0s:
Hold all THREE FULLY DEPLOYED DOMES together: foreground, rear-left and rear-right. The tents keep their completed shapes. Through the foreground window, MILA rests with subtle breathing movements.
Throughout this final shot, a DIFFERENT coworker in a light-blue shirt and dark trousers carries a mug slowly toward the camera along the unobstructed LEFT aisle. He is already visible at the start of the shot and remains visible until the video ends. His route stays beside the tents, without passing behind them. Keep enough space on the left to retain his whole body within the frame.
He continues the same ordinary walking motion from step to step. His face, clothing, mug and position remain continuous. He is separate from the seated white-shirted coworker operating the right-hand tent. The seated operator becomes hidden only when the closing fabric physically covers him. No disappearance, replacement or reset of either person.
AUDIO AND CONTINUITY
Quiet office ambience, distant typing, ventilation, a brief button click at each activation, subtle mechanism sounds, fabric rustling and footsteps. No dialogue, narration, music, subtitles or added graphics.
The desk, laptop, chair, partitions and canopy attachment points remain fixed. The same existing frame and fabric form the enclosure through continuous physical movement. Nothing materializes, changes size or passes through MILA or the furniture.
#AIVideo
🤖 Made with AI
This party is legendary 💔
Made with Seedance 2.5 on @makeugc
My workflow:
1. I used one of my workout videos as a reference so Mila would look like herself at the party.
2. I added 7 images of the original memes. Sweating Jordan Peele was on the guest list too, but the filter kept blocking that reference, so I swapped him out.
3. I came up with the idea and the hook, then wrote a rough script. I gave that draft to GPT-6 Astra to turn it into a Seedance prompt.
4. I added the music and converted the video to 60 fps. Done
FULL PROMPT (about 13K characters) in the replies 👇
#AIVideo
Alpha Mom retweeted
POV: it's 3am in Miami and you're the guy buying cocktails for mermaids
Tested Seedance 2.5 on @makeugc. Costs $1 to try it yourself, setup in the replies 👇
Every group has three drinkers: the fun one, the sick one, and the one you never invite to the pool again.
Which one are you after two drinks?
Prompt:
Amateur vertical iPhone video, 9:16, filmed at 2am at a Miami hotel pool with the phone's harsh built-in flash, shaky handheld, grainy, slight motion blur, auto-exposure flicker, candid real home video look, not cinematic, no music. The man filming is kneeling on the pool edge, camera held at his chest height, about one and a half meters from them, centered and angled a little down at them, so we see their faces, the lit water surface around them and their tails under the water behind them; all three are fully in the frame side by side the whole time; the camera never moves to a side angle and never crops anyone out. Layout locked for the whole video: the three mermaids are in the water right in front of him, resting their forearms on the same pool edge side by side, floating low with the water up to their collarbones; on the edge in front of them stand three wide glasses of bright pink cocktail with ice, one in front of each mermaid, and in each glass stands a bunch of exactly five thin see-through colored straws: lime green straws in the LEFT one's glass, neon blue straws in the RIGHT one's glass, bright yellow straws in the CENTER one's glass; behind them the bright lit turquoise pool water, clear enough to see into, the far side of the pool, palm trees and dim hotel lights.
The creatures: three real mermaids. All three are beautiful Miami women with hugely overfilled, giant, glossy duck lips, so swollen and stiff they can barely open their mouths, clearly visible from the very first frame, long lashes, long almond acrylic nails, seashell bikini tops right at the waterline. It is obvious they are mermaids the whole time: under the clear lit turquoise water their long shimmering scaled fish tails are clearly visible stretching out behind them, each tail its own color. When a tail fin comes out of the water, it rises about two meters behind its owner, clearly separated from her head by open water; a tail fin never appears right behind or above anyone's head.
Realism: their faces look like real women filmed on a phone, not CGI, not dolls, not airbrushed. Real human skin with visible pores, fine baby hairs, tiny natural imperfections, natural skin sheen and water droplets under the harsh flash, light everyday makeup. Only the lips are exaggerated; everything else about the faces is natural and real.
Three clearly different women, not twins:
LEFT: tanned Latina with long dark-brown wet curly hair, small gold hoop earrings, nude-caramel glossy lips, emerald tail.
CENTER: light-tanned girl with platinum blonde hair slicked back wet into a high ponytail, soft pink glossy lips, pearl-white tail.
RIGHT: East Asian girl with a sleek wet black bob, rose-mauve glossy lips, deep blue tail.
The man's hand: the only male hand in the video is the man's own hand from the camera side: a big tanned masculine hand with hairy wrist, thick fingers and short nails. Each mermaid has only her own two hands; no extra hands appear.
Lips: the LEFT and RIGHT ones drink only through straws, so their lips stay clean and glossy the whole video. Only the CENTER one gets a few pink drops on her lips and chin, and only after her gulp at 8 seconds.
Water: the pool water stays clear turquoise everywhere until 9 seconds. Only then the water around the CENTER one turns pink, exactly as described below. The pink stays as one soft cloud around her, about a meter wide, and never fills the whole pool; the water around the LEFT and RIGHT ones and the rest of the pool stays clear turquoise.
Voices: they speak slowly with lazy, breathy voices, barely moving their giant stiff lips, teeth not visible.
Important: all three are alive and moving every second, eyes open: no one ever freezes, closes her eyes or stares blankly while another acts. They glance at each other, at the glasses and at the camera, react to each other with real, different, asynchronous movements. Each of the three reacts to the drink in her own completely different way, as described below; the two tails move in clearly different ways. Only the LEFT one giggles; the CENTER one never laughs or smiles.
0-2s: The flash hits all three faces at once, all three in frame, giant lips first thing you see. The man's hand pushes the CENTER one's glass a little closer to her and pulls back out of the frame before 2 seconds. The LEFT one picks up her own glass first, the other two watch her.
2-5s: The LEFT one puts the five lime green straws from her own glass between her giant lips and sucks: the pink cocktail visibly rises in all five green straws at once and the level in her glass drops fast. She puts the glass down. One second later her emerald tail fin bursts up out of the water two meters behind her and thrashes fast and wildly side to side, slapping the surface again and again and splashing water high. She giggles drunkenly, "hahaha", and sways with a dizzy happy look. The RIGHT one stares at the thrashing tail, the CENTER one watches with a flat face.
5-8s: The RIGHT one picks up her own glass, puts its five neon blue straws between her lips and sucks, the pink rising in all five blue straws, then puts the glass down. Right away she looks sick: her cheeks puff out, she presses her fingers over her lips, her eyes water, she swallows hard. Her deep blue tail rises slowly and heavily out of the water two meters behind her, slaps down hard once, rises again slowly, slaps down a second time, then flops limply onto the surface and slides back under. Next to her the LEFT one is still swaying and giggling quietly.
8-12s: The CENTER one pulls the five yellow straws out of her glass, drops them on the edge, and drinks the whole cocktail straight over the rim in one long gulp without stopping. She puts the empty glass down. Her face doesn't change at all, she just blinks once, her tail stays calm. Then, a second later, the clear turquoise water right around her slowly starts turning pink, the same bright pink as the cocktail, a soft pink cloud spreading out from her body through the water, and her pearl-white tail under the water slowly turns pink too. She keeps the same flat face. The LEFT one stops giggling and the RIGHT one, still holding her lips, both look down at the pink water spreading around her, then at her face, and both slide a little away from her along the edge, staying in the frame.
12-13s: The CENTER one slides her empty glass across the edge toward the camera with two fingers, without a word.
13-15s: Quiet held moment: the CENTER one looks straight into the lens with a flat, sober face, floating in her pink cloud of water, her tail pink under the surface; the LEFT and RIGHT ones a little further away from her on both sides, still in the frame, the LEFT one swaying slightly, the RIGHT one still a little sick, fingers near her lips, both side-eyeing the pink water. No one speaks.
Sound: pool filter hum, soft water splashes, ice clinking in the glasses, loud slurping through many straws, one long gulp, fast wild tail slapping and splashing from the LEFT one's tail, two slow heavy tail slaps from the RIGHT one's tail, drunken giggles from the LEFT one only, the glass sliding on stone, the man's quiet stunned breathing. Faces stay sharp and lit by the flash the whole time.
🤝 Paid partnership · 🤖 Made with AI
POV: it's 3am in Miami and you're the guy feeding a live octopus to mermaids
Tested Seedance 2.5 on @makeugc. Costs $1 to try it yourself, setup in the replies 👇
Menu so far: sushi, caviar, pasta. Tonight the food fought back.
Trick for faces that don't look plastic: describe the skin, not the beauty. Pores, baby hairs, water drops under the flash.
Prompt:
Amateur vertical iPhone video, 9:16, filmed at 2am at a Miami hotel pool with the phone's harsh built-in flash, shaky handheld, grainy, slight motion blur, auto-exposure flicker, candid real home video look, not cinematic, no music. The man filming is kneeling on the pool edge, camera low, head-on and centered, about one meter from their faces, wide enough that all three mermaids are fully in the frame side by side the whole time; the camera never moves to a side angle and never crops anyone out. Layout locked for the whole video: the three mermaids are in the water right in front of him, leaning on the same pool edge side by side; a small wet white plate with no ice on it and one live reddish-purple octopus, about the size of a hand, sits on the edge right in the center, directly in front of the CENTER mermaid; behind them the dark pool water, the far side of the pool, palm trees and dim hotel lights.
The creatures: three real mermaids leaning on the pool edge with their forearms. All three are beautiful Miami women with hugely overfilled, giant, glossy duck lips, so swollen and stiff they can barely open their mouths, clearly visible from the very first frame, long lashes, long almond acrylic nails. Each wears a seashell bikini top, a little cleavage visible just above the pool edge. Their shimmering fish tails stretch out in the water far behind them, so it is obvious they are mermaids. Tail fins only ever appear far behind them near the left or right edge of the frame; a tail fin never appears behind or above anyone's head.
Realism: their faces look like real women filmed on a phone, not CGI, not dolls, not airbrushed. Real human skin with visible pores, fine baby hairs, tiny natural imperfections, natural skin sheen and water droplets under the harsh flash, light everyday makeup. Only the lips are exaggerated; everything else about the faces is natural and real.
Three clearly different women, not twins, new faces:
LEFT: tanned Latina with long dark-brown wet curly hair, small gold hoop earrings, nude-caramel glossy lips, emerald tail.
CENTER: light-tanned girl with platinum blonde hair slicked back wet into a high ponytail, soft pink glossy lips, pearl-white tail.
RIGHT: East Asian girl with a sleek wet black bob, rose-mauve glossy lips, deep blue tail.
The man's hand: the only male hand in the video is the man's own hand from the camera side: a big tanned masculine hand with hairy wrist, thick fingers and short nails. Each mermaid has only her own two hands; no extra hands appear.
The octopus: there is exactly one octopus in the whole video; it never duplicates or splits. It moves slowly and softly like a real octopus, it never jumps. It stays whole and alive the entire video: its body is smooth and evenly reddish-purple all over at every moment, with no white spots, no pale patches and no missing pieces. Nothing white ever sticks to it.
Voices: they speak slowly with lazy, breathy voices, barely moving their giant stiff lips, teeth not visible.
Important: nobody laughs at any point. All three are alive and moving every second, eyes open: no one ever freezes, closes her eyes or stares blankly while another acts. They glance at each other, at the octopus and at the camera, shift their weight on the edge, react to each other with real, different, asynchronous movements.
0-2s: The flash hits all three faces at once, all three in frame, giant lips first thing you see. The man's hand pushes the plate with the live octopus a little closer to them and pulls back out of the frame before 2 seconds. The octopus slowly moves its tentacles on the wet plate. The CENTER one leans in to look at it and says slowly: "Is it alive?" The LEFT one wrinkles her nose, the RIGHT one leans closer, curious.
2-5s: The CENTER one leans her face low over the plate, very close to the octopus. The octopus lifts its tentacles, grabs onto her face and pulls itself up onto her mouth, its round body covering her giant lips, its tentacles spreading across her cheeks and chin. Her eyes go wide, she grabs the octopus with both hands. The LEFT one jerks back, the RIGHT one covers her own mouth with her hand, both watching.
5-8s: The CENTER one pulls the octopus away from her face with both hands; it stretches, holding on by suction, then comes off with a loud wet POP. She holds the whole, unharmed octopus up in the air in front of her, wriggling, its body smooth and evenly colored. Only now her lips change: they are visibly even bigger and puffier than before, glossy, slightly redder, with a faint ring of small round suction marks around her mouth. The other two still have their original lips and no marks.
8-11s: The CENTER one, still holding the octopus up in one hand, touches her new bigger lips with the fingertips of her other hand, eyes wide, then looks straight into the lens and says slowly, impressed: "Oh... I like it." The LEFT and RIGHT ones stare at her lips, then at each other, with open envy.
11-15s: The LEFT one takes the whole octopus out of the CENTER one's hand and presses it onto her own lips with both hands, holding it there, eyes open, looking at the camera over it. The RIGHT one reaches over and taps the LEFT one's shoulder impatiently and says slowly: "My turn." The CENTER one keeps touching her lips, pleased.
Sound: pool filter hum, water splashes, soft wet sounds of tentacles, one loud wet suction pop, lazy breathy voices, the man's quiet stunned breathing. No laughter. Faces stay sharp and lit by the flash the whole time.
I need this at work
Made with Seedance 2.5 on @makeugc
PROMPT ⬇️
Create a 15-second photorealistic live-action office comedy, landscape 16:9. MILA activates a fold-out privacy canopy over her workstation and settles down for a nap. The absurd invention is presented with the everyday realism of an ordinary office recording.
CHARACTER
MILA — a beautiful American Instagram-style brunette model and performer, 20. Long dark-brown hair in a high ponytail, natural skin texture, glossy lips, expressive eyes, soft glam makeup and delicate sparkly stud earrings. Slim athletic figure with a very large, full bust, very full rounded buttocks, a narrow waist, flat stomach, lean arms and slender legs.
She wears an open, fitted navy blazer over a cream scoop-neck top showing cleavage, a matching short navy pencil skirt and black closed-toe heels. The clothes have ordinary fabric texture, seams and natural creases. A soft grey travel pillow supports her neck. Her appearance and outfit remain consistent throughout.
SETTING
An ordinary American open-plan office during working hours. Low grey fabric cubicle partitions, off-white desks and drawer units, black monitors, folders, pens, desk phones, a few plants and grey carpet. A low white acoustic-tile ceiling has rows of long rectangular fluorescent-style light fixtures.
MILA sits in a black wheeled office chair at a desk with an open laptop. A folded grey fabric canopy and its curved support ribs are already visibly attached to her workstation. A round activation button is mounted on the partition within easy reach.
There are THREE clearly separated tent-equipped workstations: MILA's in the foreground, another behind her on the left, and a third behind her on the right. Leave enough space between them for the final camera angle to show all three enclosures.
All three use the same rounded, dome-shaped retractable tent. Bowed support ribs form a vaulted roof and curved side walls, with grey fabric extending almost to the carpet. The completed enclosure has real depth and surrounds the entire desk and reclined chair. Its small clear window is part of the curved fabric wall at the seated occupant's head height.
The folded ribs and attached fabric already exist before activation. The same structure unfolds into the dome; it does not change into a different device. No flat hanging curtains, rectangular fabric boxes or roller blinds.
Several adult coworkers in normal American office clothes quietly continue their work.
CAMERA
DV 16mm tape camcorder handheld feel.
A coworker films MILA from the aisle, with restrained handheld movement and ordinary observational framing. The camera and operator never appear.
Use a moderately wide perspective and an oblique three-quarter angle that shows the depth of the desk and tent. Substantial depth of field: nearby partitions, folders, ceiling fixtures and background coworkers remain legible. Avoid a symmetrical front-on product-demonstration composition or portrait-style background blur.
Subtle hand movement and small framing adjustments. No floating camera, cinematic orbit or dramatic push-in.
Exactly three shots, with cuts only at 2.5s and 8.5s. Each tent deployment is shown continuously within its shot. The entire final wide shot is one uninterrupted take with no hidden cuts or time jumps.
The opening three-quarter medium shot includes MILA's face, full bust, waist, the activation button and the folded canopy. Her face is clearly readable without cropping the image into a tight face-only portrait.
LOOK AND LIGHTING — ESSENTIAL
Plain, naturally exposed office footage. Bright neutral office whites, a very slight cool fluorescent cast, restrained saturation and clear detail across both the subject and the surrounding room. Expose for the occupied office: pale desks and partitions stay bright, with readable midtones on MILA's face and navy jacket. Avoid a dim, warm, cinematic treatment.
MILA receives the same overhead illumination as the desks and coworkers around her. Broad, overlapping light from the rows of ceiling fixtures produces soft shadows beneath her brow, nose and chin. Reflected light from pale desks, walls and ceiling gently fills these shadows. Her face has no separate frontal beauty light or rim light.
Preserve ordinary facial detail at this viewing distance: subtle variation in skin color, small creases around the eyes and mouth, slight natural asymmetry and individual stray hairs. Keep her makeup as described. Her face, hands, clothes and the office share the same focus, exposure and recording texture. No isolated smooth, retouched face against a detailed background.
Keep only subtle consumer-video softness and recording texture. Faces, fabric and background desks remain readable. No heavy VHS filter, excessive blur, added haze, exaggerated grain or artificial face sharpening.
The grey canopy has lightweight woven fabric, visible stitching, uneven folds and tension around its curved supports. Maintain natural differences between cloth, skin, plastic and metal.
As the canopy closes, it progressively blocks the overhead light. Only the enclosed workstation becomes darker. A subdued warm desk light then becomes noticeable on MILA's face through the clear window. The surrounding office retains exactly the same bright neutral exposure and color. The warm light stays local, without turning her skin orange or changing the whole room.
No beauty retouching, glossy commercial grading, golden-hour sunlight, dramatic rim light or teal-and-orange treatment.
STYLE
Dry, understated workplace humor. MILA treats the device as a completely normal office convenience. Relaxed, slightly tired behavior and natural blinking. Her brief satisfied smile gently relaxes as she settles into the pillow. Her jaw and lips relax before she closes her eyes; she does not maintain a fixed model's smile while sleeping. Small natural breathing movements continue.
Coworkers do not perform exaggerated reactions.
STORYBOARD — 15 SECONDS
0.0–2.5s — THE BUTTON
Begin directly on MILA already seated with the neck pillow in place. The folded canopy is visible above the partition.
She reaches out, presses the round button once, withdraws her hand and eases back into the chair. Her head settles into the pillow. The canopy begins moving immediately after the press.
2.5–8.5s — THE WORKSTATION CLOSES
Cut to a wider three-quarter view showing the desk, chair and entire moving canopy.
Hold this shot continuously throughout the complete deployment.
The leading curved hoop rises from the folded assembly, sweeps upward and forward over MILA's head, then travels downward outside the chair. The other bowed ribs spread behind it, drawing the attached fabric into a rounded, three-dimensional dome.
Show the entire structure, including the roof, curved side walls and descending lower edge. The fabric stays attached to its supports. Folds stretch out progressively; loose edges sway slightly and settle. The frame clears MILA, the laptop and the chair.
By 7.5s, the dome is FULLY CLOSED around the desk and reclined chair. Its lower fabric edge reaches almost to the carpet, enclosing her legs and the chair base. The small transparent window remains at face height. This is a complete rounded tent, not a rectangular curtain lowered in front of an otherwise open cubicle.
From 7.5–8.5s, hold the completed shape. MILA is visible through the window with her head supported and eyes closed. The soft warm interior light becomes noticeable on her face.
8.5–15.0s — BUSINESS AS USUAL
One uninterrupted oblique wide shot of the same office. Frame all THREE workstations together without MILA's foreground dome blocking the two behind it.
8.5–9.0s:
MILA's completed dome is in the foreground. An IDENTICAL FULLY CLOSED DOME is clearly visible behind her on the LEFT. Behind her on the RIGHT, a seated coworker in a white shirt is at the third workstation, whose identical canopy is still folded.
9.0–12.5s:
The seated coworker presses their own button and reclines. The RIGHT-HAND canopy performs the SAME COMPLETE DEPLOYMENT as MILA's: the existing curved hoop rises, sweeps over the occupied workstation and descends around the outside of the chair. The attached ribs and fabric spread into the same full rounded dome. Its lower edge reaches almost to the carpet. Finish the entire movement by 12.5s.
12.5–15.0s:
Hold all THREE FULLY DEPLOYED DOMES together: foreground, rear-left and rear-right. The tents keep their completed shapes. Through the foreground window, MILA rests with subtle breathing movements.
Throughout this final shot, a DIFFERENT coworker in a light-blue shirt and dark trousers carries a mug slowly toward the camera along the unobstructed LEFT aisle. He is already visible at the start of the shot and remains visible until the video ends. His route stays beside the tents, without passing behind them. Keep enough space on the left to retain his whole body within the frame.
He continues the same ordinary walking motion from step to step. His face, clothing, mug and position remain continuous. He is separate from the seated white-shirted coworker operating the right-hand tent. The seated operator becomes hidden only when the closing fabric physically covers him. No disappearance, replacement or reset of either person.
AUDIO AND CONTINUITY
Quiet office ambience, distant typing, ventilation, a brief button click at each activation, subtle mechanism sounds, fabric rustling and footsteps. No dialogue, narration, music, subtitles or added graphics.
The desk, laptop, chair, partitions and canopy attachment points remain fixed. The same existing frame and fabric form the enclosure through continuous physical movement. Nothing materializes, changes size or passes through MILA or the furniture.
#AIVideo
🤖 Made with AI
This party is legendary 💔
Made with Seedance 2.5 on @makeugc
My workflow:
1. I used one of my workout videos as a reference so Mila would look like herself at the party.
2. I added 7 images of the original memes. Sweating Jordan Peele was on the guest list too, but the filter kept blocking that reference, so I swapped him out.
3. I came up with the idea and the hook, then wrote a rough script. I gave that draft to GPT-6 Astra to turn it into a Seedance prompt.
4. I added the music and converted the video to 60 fps. Done
FULL PROMPT (about 13K characters) in the replies 👇
#AIVideo
Alpha Mom retweeted
Ten seconds of peace. That's all I asked for.
Made on @makeugc (Seedance 2.5) 👇
Everyone judges AI animals by how they look. Close your eyes and listen instead.
Wolves don't bark. Most models still make them bark, because they've heard a million dogs and almost no wolves.
Here the whole story is in the sound. A low growl in the close-up that makes you tense up. Then one whistle, and the same animal starts whining like a scolded puppy.
The skin does the rest. Goosebumps the second the cloak drops, and then they slowly fade once she sinks into the hot water.
Would you whistle or run?
🤝 Paid partnership · 🤖 Made with AI
Everyone said it gets easier after 30 seconds. They lied.
Jade tried an ice bath. Made on @makeugc (Seedance 2.5). Details below 👇
Most people still try to fix AI realism through the face. Wrong place to look.
What sells this one is the stuff nobody notices. Breath vapor. A pink nose. Two empty ice bags lying on the grass.
And it's November, so it had to be a cold grey morning. Put her in a sunny backyard right now and people would scroll past without knowing why.
Same with reactions. Real people barely react in ice, they just gasp and shake. The moment a character screams, you know it's AI.
Would you last 30 seconds?
Alpha Mom retweeted
GTA VI is finally out. But there's one little problem... the game just sucked us into it.
Decided to take the excitement around GTA VI a little further with another AI experiment on @makeugc
Imagine waiting years for a game, finally sitting down with your friend to play it, and suddenly finding yourselves INSIDE the game instead.
No controllers. No respawns. Just you, your best friend, and Vice City.
Would you actually want to experience GTA VI like this?
#AIVideo
Looks like Jason and Lucia's relationship is already in trouble. And GTA VI isn't even out yet.
Decided to have a little fun with the GTA VI characters and AI on @makeugc.
Just imagine going to a game with your girlfriend and suddenly ending up on the Kiss Cam... with another girl sitting right next to you.
Jason, you've got some explaining to do.
What do you think happens next?
#AIVideo
Alpha Mom retweeted
This is what 4D cinema looks like now
Created by Seedance 2.5 on @makeugc
Prompt:👇
FORMAT: 15 seconds, vertical 9:16, one continuous handheld smartphone take with no cuts. Photorealistic real-life viral footage, filmed by a friend in the next seat inside a premium immersive 4D cinema. It must feel 100% real: real people, real hall, real practical show effects, real phone camera behavior.
REFERENCES: Motion and structure reference video - immersive cinema with a giant curved wraparound screen. Keep its structure: the person talks to camera, the camera pans to the screen, the on-screen object appears to break out of the screen into the hall, practical fog floods the seats, the camera returns to the person's reaction. Do not copy any logos, flags or branded characters from the reference.
REALISM:
- Real iPhone footage: slight sensor noise in the dark, auto-exposure pumping when fire flashes, brief highlight blowout, lens flare streaks from the strobes, natural motion blur on fast pans, rolling-shutter wobble on the strongest vibration, autofocus hunting for a split second when the smoke rushes the lens.
- Every effect in the hall is a real practical 4D show effect: propane flame jets, CO2 cryo blasts, sparkle fountains, fog and haze machines, high-power wind fans, water mist sprayers, strobe and laser rigs, seat motion and sub-bass vibration. Fire is real flame with real heat haze, physically placed on stage and side platforms, never touching the audience.
- The fighter jet exists only as a giant photorealistic projected 3D image on the curved screen, perfectly blended with the real smoke so it looks like it bursts into the hall. Correct scale, brushed grey metal, panel lines, rivets, cockpit glass reflections, glowing afterburners, heat distortion behind the engines.
- Light physics: firelight paints faces orange, strobes freeze motion for single frames, smoke catches light beams in thick volumetric shafts, phone screens in the crowd glow through the fog.
- Wind and water physics: hair and hoodie strings whip in the wind, the mist leaves real wet droplets on skin and seats, fog has weight and rolls down the aisle steps like liquid.
CHARACTER: Young East Asian woman, 22 years old. Long straight black hair, natural light makeup, oversized black hoodie, light-blue jeans, white sneakers. She holds a small clear plastic water bottle. Playful, confident, very expressive natural reactions. Her face, hair and outfit stay exactly the same for the whole video.
ENVIRONMENT: Huge dark immersive cinema hall, packed with people, many holding up phones with lit screens. Steep rows of dark blue seats, blue LED strips on every aisle step. A giant curved screen wraps around the front and sides. Black side platforms next to the screen hold flame-jet nozzles and sparkle fountains. Ceiling truss with strobes, laser heads and fog outlets. Big wind fans in the walls.
TIMELINE:
0.0-2.5s: Medium close-up. She sits in her seat, leans toward the camera, raises one eyebrow with a sly half-smile and says: "Dude... you're not ready for this." Blue screen light flickers across her face, the hall is quiet with a low ambient rumble.
2.5-4.5s: Fast smooth pan right to the screen. A stormy sky over a black ocean, lightning flashes inside the clouds. Two grey fighter jets appear far away, skimming low over the waves straight toward the audience. The engine roar builds from the rear speakers forward. The crowd lifts their phones, a few people point.
4.5-6.5s: The lead jet fires. A missile streaks across the screen and hits a warship on the horizon. A massive fireball fills the screen. At the same instant real propane flame jets roar up on both side platforms, four tall columns of fire, with a heavy WHOOMP. A wave of heat haze ripples across the front rows. The phone exposure blows out white, then recovers. People flinch back in their seats.
6.5-8.5s: The lead jet rushes at the screen, afterburners blazing orange. Its nose appears to pierce the screen. At this moment CO2 cannons blast white plumes from the ceiling with a loud hiss, thick dark smoke and white fog pour out of the vents around the screen and roll down the aisles, swallowing the blue LED lights. Red and white strobes hammer the hall. The giant jet nose and cockpit seem to hang right above the front rows inside the smoke, glowing with reflected fire.
8.5-10.5s: A second explosion fills the screen behind the jet, sparkle fountains erupt from the stage floor in golden showers, laser beams sweep through the smoke like tracer fire. The seats shake hard, the camera rattles with the sub-bass. A blast of water mist sprays over the crowd. People scream, laugh and cover their heads.
10.5-12.5s: The camera tilts up. The jet's huge belly and twin glowing engines fill the top of the frame as it seems to roar straight over the audience. A powerful gust from the wind fans hits the hall, hair and smoke whip backward. The engine sound sweeps from the front speakers over the heads to the back of the hall with a deep sonic boom.
12.5-15.0s: Quick swing back to the girl. She is chest-deep in thick white fog, hair blown back, small water droplets on her cheeks, eyes wide, mouth open. Behind her the flame jets fire one last time, lighting her face orange. She bursts out laughing, grips the bottle and shouts into the camera: "Dude! What was THAT?!" The fog keeps rolling, the screen glows red behind the smoke.
CAMERA: One smartphone, handheld, from the next seat, at chest height. Smooth fast pan to the screen, a tilt up for the overhead pass, a fast swing back to her. Real shake on every boom, a stronger rattle from the seat vibration, small focus hunting in the smoke, natural exposure flicker from fire and strobes. One take, no cuts, no stabilizer-perfect motion.
AUDIO & DIALOGUE: English only. Lines: "Dude... you're not ready for this." and "Dude! What was THAT?!" Full cinema surround: rising jet turbine whine and roar, missile whoosh, deep explosion booms, sub-bass rumble you can feel, WHOOMP of the propane flame jets, loud hiss of the CO2 cannons, crackle of the sparkle fountains, wind gusts, a sonic boom, rattling seats, the audience screaming, gasping and cheering. No music, no voiceover.
CONTINUITY: The girl stays in the same seat the whole time. The water bottle stays in her hand. Fog and smoke only grow and never vanish suddenly. Flame jets stay on the stage platforms. The jet is visible on screen until it passes overhead. The crowd stays seated. Her hair is blown back only after the wind gust.
NEGATIVE CONSTRAINTS: no cuts, no text, no subtitles, no logos, no flags, no branded characters, no cartoon or anime look, no plastic CGI, no video-game graphics, no real fire touching people, no burned or injured people, no real damage to the hall, no passenger airliner, no face changes, no extra fingers, no distorted hands, no frozen or duplicated crowd faces, no slow-motion, no gimbal-perfect camera.
Alpha Mom retweeted
how do you afford a lamborghini but can't remember to take the nozzle out
Created by Seedance 2.5 on @makeugc
Prompt:👇
FORMAT: 15 seconds, vertical 9:16, 60 fps, single continuous handheld take, no cuts. Smooth 60i-style video motion typical of NTSC DV camcorders. Looks like genuine amateur footage of a real accident, not a movie. Shot on a DV 16mm tape camcorder: slightly soft interlaced image, mild chroma noise, warm-shifted color, tape grain, subtle dropout flicker, auto-exposure pumping and brief white blowout on the fire flash.
REALISM: Strictly real-world physics and real accident behavior, nothing exaggerated. Real gasoline fire: dirty orange flames, heavy black smoke, heat shimmer, burning fuel spreading flat across the concrete. The ignition is a real vapor flash: a fast low wide whoosh of fire across the spilled fuel and vapor, not a tall cinematic fireball, no mushroom cloud. Real laminated windshield behavior: it cracks into a spiderweb around the impact point and sags inward, small glass crumbs and chips spray into the cabin, the glass does not vanish. Debris is limited and has correct weight, arcs and bounces. Unglamorous, chaotic, believable.
CAMERA: Point-of-view from the driver's seat of an ordinary dark sedan, filmed by the driver holding the camcorder at chest height. Steering wheel, dashboard and windshield always in the lower frame. Constant hand shake, misaligned tilted framing, delayed focus pulls hunting between dashboard and the scene outside, clumsy zoom-ins that overshoot, sudden zoom-outs, imperfect off-center shots, hard jolts on impacts. The camera never flips up toward the operator. Camcorder and operator's face never appear. Only the driver's right hand and grey hoodie sleeve are visible when tapping the wheel, honking and shifting.
CHARACTERS: Driver (unseen, male voice, 30s, impatient, then terrified). Lamborghini driver unseen behind dark tinted glass.
VEHICLE: Brand-new Lamborghini Revuelto in glossy neon lime green with black carbon accents, low stance, Y-shaped headlights, quad center exhaust. Spotless, canopy lights reflecting on its paint.
ENVIRONMENT: Ordinary European fuel station under a white-and-blue canopy, overcast daylight, bare trees and small houses behind, grey concrete. The Lamborghini is at a single pump on a raised island 6-7 meters ahead of our car, fuel nozzle inserted in its filler, black hose sagging to the pump, pump display digits running.
TIMELINE:
0.0-2.5s: Shaky view of the idling Lamborghini, deep burble with light crackles. Camcorder zooms in clumsily, overshoots, focus hunts onto the dashboard, then zooms back out. Driver's fingers drum impatiently on the wheel.
2.5-4.0s: Right hand slams the wheel center twice, two loud horn blasts, camera jerking with each. Driver shouts: "Hey! You sleeping in there? Move it!"
4.0-5.5s: Lamborghini answers with two hard revs: short orange flame pops and sharp bangs from the exhaust, our cabin vibrating slightly. Driver smirks: "Oh, you wanna show off?"
5.5-7.0s: Lamborghini launches hard, rear tires chirping with a light puff of tire smoke. Nozzle still in its tank: the hose snaps tight and does not release. The pump is yanked forward, tears loose from its base with a metal crunch and topples off the island onto the concrete, its steel corner scraping and throwing a short burst of sparks. The hose tears from the pump, nozzle and hose piece leave with the car. Gasoline gushes from the broken pipe in the pump base, spreading fast across the concrete.
7.0-8.5s: Lamborghini disappears down the exit road. The sparks have lit the fuel: small flames dance at the edge of the spill, spreading quickly. Driver: "No, no, no, no!" His hand grabs the gear lever and shoves it into reverse.
8.5-10.0s: Our car rolls back about 3 meters, reverse sensor beeping, camera lurching forward then back, horizon tilting. Fire spreads over the spill and the fallen pump, thick black smoke rising against the canopy, strong heat haze.
10.0-10.8s: The pooled vapor ignites all at once: a loud deep WHUMP, a wide low wall of flame rolls outward across the concrete, a hot flash hits the camera, exposure blows out for a few frames and recovers. The blast flings the pump's broken metal display panel through the air toward us. It hits the windshield with a heavy bang: the glass spiderwebs around the impact and sags inward, crumbs of glass spraying over the dashboard, steering wheel and lens. The panel slides off the hood onto the ground.
10.8-13.5s: Camera shaking wildly, dipping to the glass-covered dashboard, then back up through the cracked, sagging windshield at the fire. Driver screams: "AAAH! What the hell! What the hell!" Flames roar over the fallen pump, smoke darkens the canopy, a car alarm starts in the distance.
13.5-15.0s: Camera nearly still, framed off-center on the burning pump through the cracked glass, heat haze rippling. Faint distant Lamborghini exhaust bangs. Driver, quiet and stunned: "...he didn't even pay."
AUDIO & DIALOGUE: Raw camcorder mic, compressed and clipping on loud peaks. Idling V12 burble, finger drumming, two horn blasts, exhaust pops, tire chirp, metal crunch and scrape, pump hitting concrete, fuel gushing, ignition crackle, growing fire roar, reverse beeps, deep vapor WHUMP with mic distortion, heavy bang of the panel on the windshield, glass cracking and crumbs pinging inside the cabin, brief ear-ringing tone, distant car alarm, distant exhaust bangs. All dialogue in English only, exactly as written.
CONTINUITY: Lamborghini leaves with the nozzle and never returns. The pump stays torn off and lying on the concrete, burning. The windshield stays cracked and sagging with glass crumbs on the dashboard and wheel. The panel stays on the ground. Our car stays in its reversed position.
NEGATIVE CONSTRAINTS: no cuts, no music, no text, no subtitles, no watermark, no camera or operator face visible, no slow motion, no stuttering or dropped frames, no Hollywood fireball, no mushroom cloud, no exaggerated shockwave, no secondary explosions, no cartoon fire, no clean cinematic stabilization, no extra vehicles or people appearing, no morphing car shape or logos, no objects repairing themselves.
Alpha Mom retweeted
This is how a zombie reacts to my heroine’s superpowers 😂
Created by Genzo on @makeugc
Seedance refused to generate this, so I used Genzo. Which tool do you use to recreate trending videos?
WORKFLOW for recreating a trending video:
- Download the video you want to recreate.
- Open your AI video generator and add it as a video reference.
- Upload the same video to ChatGPT. Ask it to create a prompt that preserves the original music and character movements.
- Specify a new location and the characters you want to replace.
- Ask ChatGPT to generate two Pixar-style character reference images.
- Have ChatGPT update the prompt using those images.
- Add the prompt and both images to your video generator.
ALL YOU NEED:
- The original video
- Character reference 1
- Character reference 2
Prompt:
Photorealistic live-action dance video, VERTICAL 9:16, approximately 17.73 seconds. Match video1's duration, speed, choreography, camera, edits and music.
REFERENCES
video1 controls both dancers' movements, gestures, expressions, timing, positions, camera angles, framing, perspective, cuts and audio.
image1 replaces the nun with the male zombie. Copy his face, white eyes, hair, skin, proportions and complete outfit, including jacket, shirt, trousers and boots.
image2 replaces the background woman with this adult woman. Copy her face, athletic build, short pink-and-blue bob, hair clips, pink-and-white cropped top, pleated skirt, pink backpack and black boots with pink platforms and buckles.
image3 replaces the courtyard with this abandoned gas station: weathered canopy, reddish trim, columns, rusty pumps, hoses, deteriorated shop, cracked asphalt and dusty warm light.
PRIORITY
Video defines performance and cinematography. Character photos define identity and clothing, not fixed poses. Location photo defines surroundings and lighting, not camera framing.
ACTION
Transfer the nun's exact performance to the zombie and the background dancer's exact performance to the new woman. Preserve their separate choreography, finger gestures, head tilts, torso bends, expressions, steps and timing. Do not make different movements identical.
Follow the video throughout; these phases are orientation only:
0–3.5s: zombie close to the lens, woman behind. Copy gestures around the temples, spread fingers, head tilts and forward lean. Woman follows her original background choreography.
3.5–7s: zombie reaches toward the lens, curls fingers, draws hands toward his chin, lowers his head and returns hands to his head.
7–14s: copy hands-on-head movements, body tilts and facial changes. Woman continues her separate arm gestures.
14–16.1s: reproduce the wider full-body shot, zombie left and woman right. Copy overhead gestures, turns, arm movements, knee bends and weight shifts.
16.1s–end: reproduce the frontal framing change, remaining steps and hand movements through the original endpoint.
The video overrides approximate timing above. No added actions or zombie limping.
CAMERA AND LOCATION
Dance on the empty gas station forecourt. Preserve original performer spacing, foreground hand perspective, camera height, downward angle, movement and every cut. Keep architecture fixed across shots and render it with correct depth. Preserve full-body visibility in wider shots. No extra shots, zooms, slow motion or new ending.
REALISM
Real performers with cinematic zombie prosthetics, natural skin, hair and fabric. Match the location's warm hazy daylight and shadows. Natural skirt, jacket and backpack movement. Stable foot contact and believable weight transfer in the reference footwear. Consistent identities, clothes and accessories.
AUDIO
Preserve the exact original music and existing audio from video1, with the same starting point, tempo, pitch and synchronization. No replacement track, remix, added speech, growls or effects.
CONSTRAINTS
Exactly two dancers. No original costumes, nun veil, wooden fence, vehicles, extra people, magic, text or watermarks. No mixed identities, extra limbs, warped fingers, sliding feet or disappearing accessories.
🤝 Paid partnership · 🤖 Made with AI
This AI video turned a zombie apocalypse into a superhero playground.
Turns out, super strength makes a terrible day look fun.
Created by Seedance 2.5 on @makeugc
Prompt:
TELEKINETIC AWAKENING — ZOMBIE GAS STATION
A 30-second horizontal 16:9 photorealistic supernatural action scene. A young woman escapes a zombie-filled store at an abandoned wasteland gas station at dusk, her violet telekinetic power awakens, and she takes down EIGHTEEN zombies with seven moves: a mid-air freeze, a head-to-head collision, a barrel volley, a lifted car, a car-door shield and a shockwave. It ends with her walking alone down the empty road while the whole horde lies still behind her.
MAIN SUBJECT
The woman from Image1, an adult in her early twenties, East Asian, dark brown eyes. Hair: a choppy chin-length bob, hot pink at the roots fading to violet and bright blue at the tips, ONE small silver lightning-bolt clip on the left side. Outfit: a fitted pink-and-white sports crop top with white stripes; a pink pleated mini skirt with white inner pleats and two white stripes on the hem, with pink fitted shorts underneath; a pink backpack strapped tightly to her back with black buckle straps. Footwear: knee-high glossy black combat boots on chunky pink platform soles with pink straps, silver studs and metal rings. All fabric is dense, opaque and stays in place during every move. Athletic, toned build. Frightened at first, then cold and focused. Preserve her face, hair colour, outfit and boots EXACTLY as in Image1.
ZOMBIES
Adult men and women with grey, dusty skin, cloudy white eyes, matted hair and torn, faded, dusty clothes. Jerky, uneven movement, some lunging fast. No blood, no wounds.
LOCATION
An abandoned gas station on a desert road at dusk. Cracked asphalt lot about 40 metres wide. A small convenience store with shattered windows and a dark doorway on the left. TWO rusted fuel pumps 6 metres apart under a sagging metal canopy 5 metres high in the centre. FOUR rusted cars: CAR A, a grey sedan parked in the open lot 3 metres outside the canopy edge; CAR B, a brown hatchback near the store; CAR C, a rusted pickup beside the canopy; CAR D, a white van far out by the road. FOUR steel oil barrels stand in the open lot between the canopy and the road. Background: the empty road to the horizon and a ruined city skyline about 10 kilometres away under a heavy overcast sky. Wind blows sand and dust across the lot.
CAMERA AND LOOK
Photorealistic live-action action film, real stunt choreography. ONE light source: soft overcast dusk daylight with diffuse light, soft shadows, muted dusty palette. The only other light is the violet glow of her power reflecting on asphalt, glass and metal. Handheld shake, slight delayed autofocus, mild bloom, faint film noise. Shots last 1.5-2.5 seconds, cut after each completed move; the car lift is ONE continuous shot. No camera or crew in frame. No glossy beauty lighting, no heavy colour grading.
TELEKINESIS EFFECTS
Luminous violet energy with a deep purple edge. Thick slow purple smoke coils around her hands and forearms up to the elbow, thin electric arcs crackle between her fingers, tiny violet particles drift upward like embers. Anything she holds gets a thin glowing violet outline with short arcs and a faint air distortion, hangs with real weight and sheds dust. Each impact gives ONE sharp violet flash. Open palm to hold, fist to crush together, push to throw, palm on the ground for the shockwave. The energy stays on her hands and never recolours her hair or clothes.
CONTINUOUS STORY
00:00-00:03.5 — BREAKOUT
Start in motion: she bursts backward out of the dark store doorway, facing inside, as a zombie's hand grabs her wrist from the darkness. She twists free and falls onto the asphalt. Low wide shot: TWO zombies vault over the hood of CAR B toward her and land heavily. She scrambles back on her hands until her back hits the first fuel pump.
00:03.5-00:07 — FROZEN IN THE AIR (zombie 1)
The zombie from the store follows her out and leaps at her face. She throws up ONE open palm; violet sparks explode into smoke and arcs around her forearm, and the zombie freezes in mid-air 1 metre from her face. Close-up: looking at it, her fear turning cold, she says quietly: "Not today." She flicks her wrist; the zombie flies 10 metres back into the store wall, cracks the stucco and drops.
00:07-00:10 — HEAD TO HEAD (zombies 2-3)
She rises to her feet. The TWO zombies who vaulted CAR B rush her from left and right. She clenches her fist; both are jerked toward each other, collide head to head with a dull thud and fall.
00:10-00:15 — BARREL VOLLEY (zombies 4-7)
She walks out to the edge of the canopy. FOUR zombies stagger toward her from the road. She spreads both arms: the FOUR barrels rise together and hang in a row at chest height, glowing violet. She pushes both palms forward in ONE motion; all four barrels fly at once and knock all FOUR zombies flat, clanging and rolling. She stays at the canopy edge, CAR A 3 metres to her right, breathing hard: a tight group of SIX zombies runs out from behind CAR D toward her, and ONE more crawls to the edge of the canopy roof above her.
00:15-00:20 — THE CAR (ONE continuous shot, zombies 8-13)
Three-quarter wide shot keeping her boots, CAR A and the zombies in frame: she plants her feet and raises both hands, and CAR A lifts off the ground, glowing violet; the wheels hang loose, sand and rust pour from its underside, and the asphalt cracks under her boots. The car rises to 3 metres in the open air outside the canopy. She swings both arms in a flat arc across her front; the car sweeps through the group and knocks all SIX zombies off their feet, then lands on its roof in the open lot, rolls once and stops on its side, glass bursting out.
00:20-00:23.5 — DOOR SHIELD (zombie 14)
The zombie on the canopy roof leaps down at her from 5 metres. In the same moment she jerks her hand toward CAR C; its driver's door rips off its hinges with a metal shriek and stops 1 metre in front of her, upright, as a glowing violet shield. The falling zombie slams into the door and bounces onto the asphalt; she pushes forward and the door drops flat on top of it, pinning it. In the background, FOUR zombies come out of the store doorway.
00:23.5-00:27.5 — SHOCKWAVE AND VORTEX (zombies 15-18)
The FOUR zombies from the store surround her at arm's length. She drops into a crouch and slams one palm onto the asphalt: a low ring of violet light and air distortion bursts outward and throws all FOUR zombies 5 metres away onto their backs. As she stands, broken glass, sand and small debris rise around her into a glowing violet vortex at waist height. She opens her hand and everything drops at once.
00:27.5-00:30 — WALK AWAY
Medium side shot: she turns her head toward the defeated horde, face in clear profile, and says flatly: "Stay down." Wide shot from behind: she takes a few steps away down the empty road past CAR A lying on its side, pink backpack and platform boots clearly visible, violet smoke fading from her fingers, the ruined skyline ahead.
DIALOGUE
Two short lines in English, calm and low, never to the camera: "Not today." at 00:05 to the frozen zombie, "Stay down." at 00:28 in profile to the defeated zombies. No other speech.
SOUND
Natural and event-driven: glass crunching at the doorway, zombie groans and snarls, her fast breathing, feet landing on the car hood, a deep rumble and electric crackle as the energy appears, a low hum while she holds objects, the thud against the store wall, the double thud of the collision, four barrels clanging, the car's metal groaning, sand pouring, the crash and glass bursting, the door ripping off its hinges and the zombie slamming into it, a heavy low boom for the shockwave, the rush of the vortex and glass falling, wind and her footsteps at the end. No music, no narration.
ESSENTIAL CONTINUITY
- Order: breakout, frozen zombie, collision, barrel volley, car, door shield, shockwave and vortex, walk away.
- EIGHTEEN zombies total: 1 from the store, 2 car vaulters, 4 from the road (barrels), 6 from CAR D (car), 1 from the canopy roof (door), 4 from the store doorway (shockwave). Each is knocked down ONCE and stays down. No other zombies appear.
- She never touches lifted objects or zombies with her hands. Lifted objects have real weight and gravity, no clipping; CAR A never hits the canopy, pillars or pumps.
- The store wall stays cracked, the barrels stay scattered, CAR A stays on its side, the door from CAR C stays on the pinned zombie.
- Violet energy only on her hands and forearms, on held objects, in impact flashes, in the shockwave and in the vortex.
- Preserve her face, hair, outfit and footwear exactly as in Image1 throughout.
No slow motion, teleportation, duplicated people, flying heroine, extra dialogue, talking to camera, changing outfits, changing hair colour, lost backpack, extra limbs, distorted hands, guns, blood, gore, explosions, fire, cartoon or anime style, captions, subtitles, readable signs, watermarks.
#zombies #aivideo
Alpha Mom retweeted
Dargaville Unsolved Mysteries
Made with Seedance 2.5 on @makeugc
🤝 Paid partnership
Alpha Mom retweeted
This AI video is an absolute Pixar masterpiece💕.
Below, I’ve outlined how to create any trending video.
Created using Genzo on @makeugc.
WORKFLOW:
- Download this video.
- Open your AI generator.
- Upload the video as a reference.
- Upload the video to ChatGPT and ask it to write a prompt based on this reference, keeping the music and character movements.
- Ask it to change the location and replace the characters.
- Ask ChatGPT to generate 2 images in a Pixar style.
- Ask ChatGPT to rewrite the prompt incorporating these new references.
ALL YOU NEED:
- Reference video
- Reference image 1
- Reference image 2
OR, use my prompt and add the 2 reference images.
🔖Save this to use later while the trend is still relevant!
PROMPT:
Use video1 as the source video. Replace only the two characters and their clothing using image1 for the dancing daughter and image2 for the father filming her. Preserve the original movements, timing, location, camera work, framing, music, and other audio.
REFERENCES
video1: Master reference for choreography, duration, aspect ratio, expressions, interactions, camera work, environment, lighting, and original soundtrack.
image1: Exact appearance and clothing of the daughter.
image2: Exact appearance and clothing of the father.
CHARACTER REPLACEMENT
Replace the original girl with the daughter from image1. Preserve her face, brown eyes, skin tone, chestnut ponytail, loose face-framing strands, stylized proportions, mint-green dress with white collar and front pockets, white socks, and white sneakers.
Replace the original man with the father from image2. Preserve his face, brown eyes, skin tone, swept brown hair, short beard, build, cream knitted sweater, dark charcoal trousers, dark sneakers with white soles, and wristwatch. Do not add the original man's sunglasses.
Use both images only for character appearance and clothing. Do not copy their standing poses, studio lighting, or neutral backgrounds. Adapt the new characters to the original actions and hallway lighting.
MOVEMENTS AND TIMING
Follow video1 throughout the entire sequence. Preserve the daughter's dance choreography, including the order, direction, timing, and speed of her steps, arm gestures, knee bends, leg lifts, body tilts, and turns. Match her changing expressions and gaze to the source performance.
Preserve the father's crouching posture, leg movements, smiles, reactions, body adjustments, and phone-handling actions. He films his daughter with the original black smartphone held vertically, its rear camera facing her and its screen facing him.
Keep the original character positions, relative scale, distance between them, and movement paths. Reproduce interactions as shown without adding new gestures, touches, or dance moves. Let the daughter's ponytail and dress move naturally in response to her actions.
LOCATION AND CAMERA
Keep the source hallway unchanged: wooden floor, walls, doorways, background furnishings, ceiling light, warm illumination, shadows, and reflections.
Preserve the original vertical 9:16 format and approximately 14.1-second duration. Follow the source camera height, angle, perspective, framing, movement, and editing exactly. Do not add cuts, close-ups, zooms, or camera shake.
VISUAL STYLE
Maintain the polished stylized 3D animated family-film appearance of the character references and source video. Integrate the replacement characters into the original lighting, color palette, and depth of field. Preserve detailed hair, knitted fabric, dress texture, natural cloth motion, grounded feet, and convincing body weight.
ORIGINAL MUSIC AND AUDIO
Keep the exact original music from video1 throughout the clip, with the same timing, rhythm, tempo, and synchronization to the dance.
Preserve any other existing source audio.
Do not replace, remix, regenerate, or reinterpret the soundtrack.
Do not add music, dialogue, voice-over, or sound effects.
CONTINUITY
Only the characters' appearance and clothing change. Everything else follows video1.
Keep the same daughter and father throughout, with stable faces, hairstyles, proportions, clothing, and accessories.
Preserve the original smartphone and its movement, orientation, and grip.
Maintain continuous positions and actions between frames.
CONSTRAINTS
No additional characters or props.
No appearance changes or wardrobe changes.
No duplicated limbs, extra fingers, sliding feet, floating objects, or body intersections.
No neutral studio background.
No captions, logos, or ending titles.
No slow motion, retiming, new choreography, or altered ending.
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
meme thế giới
This party is legendary 💔
Made with Seedance 2.5 on @makeugc
My workflow:
1. I used one of my workout videos as a reference so Mila would look like herself at the party.
2. I added 7 images of the original memes. Sweating Jordan Peele was on the guest list too, but the filter kept blocking that reference, so I swapped him out.
3. I came up with the idea and the hook, then wrote a rough script. I gave that draft to GPT-6 Astra to turn it into a Seedance prompt.
4. I added the music and converted the video to 60 fps. Done
FULL PROMPT (about 13K characters) in the replies 👇
#AIVideo
Alpha Mom retweeted
Y ahora con invitados
OMG, look who I ran into at the gym 😭
Made with Seedance 2.5 on @makeugc using my character reference from the quoted post + the original meme images.
PROMPT ⬇️
Create a 17-second photorealistic gym vlog, landscape 16:9. MILA discovers famous meme characters at her gym, rapidly switching between their recognizable actions and her own spontaneous selfie reactions.
Match the photographic realism, MILA’s appearance, lighting and handheld filming of video1. The pacing is fast, funny and energetic.
REFERENCES
video1 — MILA’s exact identity, face, body proportions, voice, blue outfit, gym lighting and natural vlog performance.
image1 — Roll Safe: exact face, black leather jacket, gold watch, haircut, knowing smile and finger-to-temple gesture.
image2 — Hide the Pain Harold: exact face, white hair, beard, checked shirt and strained polite smile. Do not include his telephone.
image3 — Salt Bae: exact face, white fitted V-neck T-shirt, round dark sunglasses, tied-back hair and signature sprinkling gesture.
image4 — Confused Nick Young: exact face, white T-shirt, head angle and puzzled expression. Do not include the printed question marks.
image5 — Disaster Girl PORTRAIT CROP: use only the girl’s exact face, hair, visible clothing and subtle knowing smirk. This is an identity reference only. The final environment comes exclusively from the gym in video1.
Each image defines a separate character. Use their identities, clothing and expressions, not their original locations. The photographs never appear as photographs on screen.
CAMERA
DV 16mm tape camcorder handheld feel. POV of MILA holding the camera herself. Natural arm’s-length MEDIUM CLOSE-UP selfies alternate with outward-facing shots of nearby gym visitors.
MILA holds the camera slightly farther from her body, with her filming arm comfortably extended. Frame her from the top of her head down to her upper waist: her face, shoulders, ENTIRE blue sports bra including its lower band, full bust and a little bare midriff are visible together. Keep the lower frame edge below the sports bra. The camera is around face height with a slight downward tilt and a natural perspective. This is a close, engaging vlog composition, not a tight face-only crop. Use this same framing for the opening and EVERY selfie reaction. No zooms into MILA’s face.
Hand shake, slightly misaligned framing, delayed focus pulls, clumsy zooms toward the meme characters, imperfect shots. Keep MILA’s face and entire sports bra within her selfie frame. Camcorder never appears on screen or in reflections.
The opening selfie leads into an immediate outward camera turn and quick zoom toward the first meme. Later selfie reactions are brief vlog jump cuts. Use short motivated pans or quick cuts to reveal the next person. Do not spend time showing MILA walking between locations or slowly rotating the camera.
Each zoom quickly lands on a readable face and gesture. Keep enough stability to recognize the meme. No floating camera, cinematic orbits or slow-motion coverage.
LOOK
Soft, slightly blurry tape quality, faint tape noise, bloomed highlights under gym lighting, flickering auto-exposure, muted contrast, realistic skin tones.
Match video1 closely. Preserve believable skin texture, fabric, weight and physical movement. Natural photographic imperfections without heavy VHS effects, plastic skin or a CGI appearance.
STYLE AND PACING
Playful, spontaneous gym-vlog humor. MILA is excited, amused and increasingly baffled. Her reactions change with each discovery: raised eyebrows, suppressed laughter, an incredulous look, then sudden surprise.
Reveal each meme character ALREADY IN THE RELEVANT ACTION. Do not show a complete exercise setup, multiple repetitions or a long buildup. Each appearance quickly arrives at the recognizable gesture or expression.
In every selfie reaction, MILA is already looking slightly off-camera toward the character she has just shown when the shot begins. Her head and eyes then make a small, quick return toward the lens, as if sharing her reaction with the viewer. Match the look direction to the previous character’s position; do not repeat the same left/right direction mechanically. Avoid continuous direct-to-camera staring. Her torso and selfie framing remain steady during these small head movements.
MILA speaks only in the opening shot. All subsequent reactions are visual. No explanatory dialogue, narration, meme captions, question-mark graphics or freeze frames.
All camera turns, zooms and transitions are included within the shot timings below. Do not add transition time or extend the video.
CHARACTER
MILA — a beautiful American Instagram-style brunette model and performer, 20. Long dark-brown hair in a high ponytail, natural skin texture with a light sweat sheen, glossy lips, expressive eyes, soft glam makeup and delicate sparkly stud earrings. Slim athletic figure with a very large, full bust, very full rounded buttocks, a narrow waist, flat stomach, lean arms and slender legs.
She wears a cobalt-blue supportive sports bra with thin straps and a deep scoop neckline showing cleavage, paired with matching ultra-short fitted athletic shorts. Bare shoulders, arms and midriff. White ankle socks, sneakers off. She speaks with an American accent.
Preserve her exact face, full bust, body proportions and blue outfit from video1 in every selfie shot.
SETTING
One ordinary gym in the evening: rubber flooring, exercise mats, mirrors, dumbbell racks, workout benches, cable machines and a small drinks counter with protein tubs and shakers. Soft overhead lighting matching video1.
All characters occupy nearby areas of this same gym. They retain the recognizable clothing from their image references.
The entire video, INCLUDING THE FINAL FIRE SCENE, stays inside this gym. Keep the same mirrored walls, overhead gym lighting, rubber floor, benches and metal exercise machines visible in the final shot. The fire burns padded gym equipment within this already established room. No location change or outdoor scene.
STORYBOARD — EXACTLY 17 SECONDS
1. 0.0–2.5s — MILA’S HOOK
Start immediately on the natural arm’s-length medium close-up described above: MILA’s full face, shoulders, full bust in the ENTIRE blue sports bra, its lower band and her upper waist are all visible. The gym remains visible behind her. Keep the camera far enough away to maintain this framing throughout the opening.
Slightly breathless after exercising, she looks into the lens with excited disbelief and says:
“Look who’s at my gym!”
As she finishes, she immediately turns the camera outward toward the dumbbell rack. Her delivery is lively and conversational, with no introductory pause.
2. 2.5–5.0s — ROLL SAFE
The camera turns and quickly zooms toward the exact man from image1, still wearing his black leather jacket and gold watch.
He is ALREADY finishing a dumbbell curl with his LEFT hand when the camera finds him. He lowers the dumbbell beside his thigh, looks into MILA’s lens and immediately touches his temple with his free RIGHT index finger.
Catch the exact familiar knowing smile and finger-to-temple pose. Hold it briefly, with natural breathing and tiny facial movement. The dumbbell remains in his other hand. No additional repetition or dialogue.
3. 5.0–5.5s — MILA’S FIRST REACTION
Quick medium close-up selfie cut, keeping MILA’s face, full bust and entire blue sports bra visible. Her head is already angled slightly toward Roll Safe off-camera. She raises her eyebrows in delighted disbelief, then brings her gaze and head gently back toward the lens.
One clear reaction, no speech.
4. 5.5–8.0s — HAROLD
Quick cut to the exact older man from image2, sitting on a nearby workout bench in his original checked shirt.
He is ALREADY struggling through the last part of a dumbbell curl. He rests the weight on his thigh, looks toward MILA’s camera and immediately forces the unmistakable Harold smile: politely smiling mouth, tired eyes and visible effort he is trying to hide.
A small camera push-in makes the expression readable. Natural breathing and a slight hand tremor. No telephone or lengthy exercise sequence.
5. 8.0–8.5s — MILA HOLDS BACK LAUGHTER
Quick medium close-up selfie with the same face-to-upper-waist framing. MILA is already looking slightly toward Harold off-camera. She presses her lips together to suppress a laugh, then makes a small head-and-eye turn back to the lens.
No speech.
6. 8.5–11.0s — SALT BAE’S PROTEIN
Quick reveal of the exact man from image3 at the gym’s drinks counter, preserving his white fitted T-shirt, sunglasses and tied-back hair.
He ALREADY has a pinch of white protein powder raised when the camera finds him. He immediately performs his famous sprinkling gesture: elbow raised, wrist bent downward, powder trickling past his forearm into an open shaker.
The shaker’s opening is directly beneath the falling powder. Keep his face, signature arm position and shaker visible together. He performs the absurd ritual with complete seriousness.
A brief clumsy zoom emphasizes the gesture. Real powder and gravity, with only a small natural dusting.
7. 11.0–11.5s — MILA’S INCREDULOUS LOOK
Quick medium close-up selfie with her full face and entire sports bra visible. MILA initially looks slightly toward Salt Bae off-camera, eyebrows raised and mouth slightly open. She then turns her head and eyes back toward the lens, silently communicating: “Are you seeing this?”
No speech.
8. 11.5–13.5s — CONFUSED NICK YOUNG
Quick pan to the exact man from image4 beside a nearby cable machine, wearing his white T-shirt.
He has just seen the protein ritual. As the camera lands, he turns toward the lens, pulls his head back slightly, squints and makes the exact familiar puzzled half-smile.
A quick push-in catches the recognizable expression. No floating question marks, text or dialogue.
9. 13.5–14.0s — MILA NOTICES THE FINAL SURPRISE
Quick medium close-up selfie, preserving the face-to-upper-waist framing. MILA is already looking slightly off-camera toward the area beside Nick Young. Her eyes widen as a warm flicker catches her attention. She makes a brief head-and-eye return toward the lens, then immediately starts turning the camera toward the flicker. No speech or prolonged reaction.
10. 14.0–17.0s — DISASTER GIRL INSIDE THE GYM
The camera turn reveals the exact girl from image5 in the RIGHT foreground, filmed near her eye level.
Deeper in the LEFT background, the SAME INDOOR GYM FROM video1 remains visible: its mirrored wall, rubber floor, overhead ceiling lights, workout benches and metal machine frames. Flames visibly rise from the upholstery of a workout bench and adjacent padded gym equipment INSIDE THIS ROOM. Smoke rises toward the gym ceiling; orange firelight reflects in the same mirrors. Preserve the established gym architecture throughout the shot. image5 supplies only the girl’s identity and expression; it supplies no background or location.
The girl is already looking toward the fire when the shot begins. She immediately turns her head back over her shoulder toward MILA’s camera and forms the exact subtle, knowing half-smile from image5.
Match her recognizable face angle, relaxed eyelids and hair beside her cheek. No broad grin or laughter.
Her face remains large in the right foreground while the burning equipment stays clearly visible behind her on the left. Keep a clear foreground gap between her and the distant flames.
Hold the final smirk for approximately the last second, with natural breathing, handheld tremor and flickering fire. End immediately on this image. No final selfie, explanation, explosion or injury.
AUDIO
MILA’s natural American voice and lively delivery match video1. Her only spoken line is:
“Look who’s at my gym!”
Natural gym ambience, breathing, small equipment sounds and subtle camera-handling noise. Fire crackling becomes audible during the final reveal.
No background music, laugh track, added meme sound effects or other dialogue.
CONTINUITY
Maintain MILA’s exact identity, body proportions and outfit across every selfie reaction. Keep her face, full bust and entire blue sports bra visible in the consistent medium close-up framing. Each reaction begins with her looking toward the previous character before she briefly reconnects with the lens. Each meme character retains their own reference face, clothing and recognizable expression.
Keep objects in the correct hands and movement physically believable. No morphing between people, duplicated limbs or changing faces.
Preserve the fast rhythm: MILA → meme → MILA reaction → next meme. Each character is caught mid-action, with no unnecessary setup. All scenes remain inside the same gym. Disaster Girl is the final shot.
#AIVideo
Alpha Mom retweeted
Hay videos de minas en gym he has con IA para farmear followers.
Me pasó a un amigo. 🫣😝
Made with Seedance 2.5 on @makeugc (native 15-second video, no editing)
PROMPT ⬇️
**CAMERA:**
DV 16mm tape camcorder handheld feel. POV of MILA holding the camera herself, occasionally propping it on the floor or a mat for hands-free core shots. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder never appears on screen.
**LOOK:**
Soft, slightly blurry tape quality, faint tape noise, bloomed highlights under gym lighting, flickering auto-exposure, muted contrast, realistic skin tones.
**STYLE:**
Playful, self-deprecating gym-vlog tone — genuine strain mixed with humor, complaining about core work while still pushing through it. Quick handheld cuts, energy staying light and funny throughout rather than fully exhausted.
**Character**
MILA — a beautiful American Instagram-style brunette model and performer, 20. Long dark-brown hair in a high ponytail, glowing skin with a light sweat sheen, glossy lips, expressive eyes, soft glam makeup and delicate sparkly stud earrings. Slim athletic figure with a very large, full bust, very full rounded buttocks, a narrow waist, flat stomach and lean arms and legs.
She wears a cobalt-blue supportive sports bra with thin straps and a deep scoop neckline showing cleavage, paired with matching ultra-short fitted athletic shorts. Bare shoulders, arms and midriff. White ankle socks, sneakers off. She speaks with an American accent.
**Setting**
A gym mat area in the evening — mirror wall nearby, water bottle on the floor, soft overhead lighting, other equipment visible in the background.
**Storyboard (15s, 6 shots)**
1. *(~2.5s, propped camera, medium shot)* She lies down on the mat, propping up on her elbows, already sighing dramatically. MILA: “Core day. Pray for me.”
2. *(~2.5s, propped camera, plank position)* She holds a plank, arms shaking slightly, talking through gritted teeth. MILA (strained): “Why am I shaking already?”
3. *(~2.5s, medium propped shot, crunches)* She moves into a set of crunches, breathing hard, complaining between reps. MILA: “This looked way easier online.”
4. *(~2s, macro insert, shallow DOF)* Close-up on her hands gripping the mat edges during a leg raise, abs visibly working. No dialogue — ambient gym sound only.
5. *(~2.5s, handheld, leg raises)* She finishes a slow leg raise set, flopping back onto the mat immediately after, laughing at herself. MILA (breathless): “Yep—my abs just quit.”
6. *(~3s, arm’s-length selfie finish)* Still lying on the mat, she lifts the camera above her face (camera no visible), grinning tiredly. MILA: “Same time tomorrow? No promises.”
#AIVideo
Alpha Mom retweeted
This AI video turned a zombie apocalypse into a superhero playground.
Turns out, super strength makes a terrible day look fun.
Created by Seedance 2.5 on @makeugc
Prompt:
TELEKINETIC AWAKENING — ZOMBIE GAS STATION
A 30-second horizontal 16:9 photorealistic supernatural action scene. A young woman escapes a zombie-filled store at an abandoned wasteland gas station at dusk, her violet telekinetic power awakens, and she takes down EIGHTEEN zombies with seven moves: a mid-air freeze, a head-to-head collision, a barrel volley, a lifted car, a car-door shield and a shockwave. It ends with her walking alone down the empty road while the whole horde lies still behind her.
MAIN SUBJECT
The woman from Image1, an adult in her early twenties, East Asian, dark brown eyes. Hair: a choppy chin-length bob, hot pink at the roots fading to violet and bright blue at the tips, ONE small silver lightning-bolt clip on the left side. Outfit: a fitted pink-and-white sports crop top with white stripes; a pink pleated mini skirt with white inner pleats and two white stripes on the hem, with pink fitted shorts underneath; a pink backpack strapped tightly to her back with black buckle straps. Footwear: knee-high glossy black combat boots on chunky pink platform soles with pink straps, silver studs and metal rings. All fabric is dense, opaque and stays in place during every move. Athletic, toned build. Frightened at first, then cold and focused. Preserve her face, hair colour, outfit and boots EXACTLY as in Image1.
ZOMBIES
Adult men and women with grey, dusty skin, cloudy white eyes, matted hair and torn, faded, dusty clothes. Jerky, uneven movement, some lunging fast. No blood, no wounds.
LOCATION
An abandoned gas station on a desert road at dusk. Cracked asphalt lot about 40 metres wide. A small convenience store with shattered windows and a dark doorway on the left. TWO rusted fuel pumps 6 metres apart under a sagging metal canopy 5 metres high in the centre. FOUR rusted cars: CAR A, a grey sedan parked in the open lot 3 metres outside the canopy edge; CAR B, a brown hatchback near the store; CAR C, a rusted pickup beside the canopy; CAR D, a white van far out by the road. FOUR steel oil barrels stand in the open lot between the canopy and the road. Background: the empty road to the horizon and a ruined city skyline about 10 kilometres away under a heavy overcast sky. Wind blows sand and dust across the lot.
CAMERA AND LOOK
Photorealistic live-action action film, real stunt choreography. ONE light source: soft overcast dusk daylight with diffuse light, soft shadows, muted dusty palette. The only other light is the violet glow of her power reflecting on asphalt, glass and metal. Handheld shake, slight delayed autofocus, mild bloom, faint film noise. Shots last 1.5-2.5 seconds, cut after each completed move; the car lift is ONE continuous shot. No camera or crew in frame. No glossy beauty lighting, no heavy colour grading.
TELEKINESIS EFFECTS
Luminous violet energy with a deep purple edge. Thick slow purple smoke coils around her hands and forearms up to the elbow, thin electric arcs crackle between her fingers, tiny violet particles drift upward like embers. Anything she holds gets a thin glowing violet outline with short arcs and a faint air distortion, hangs with real weight and sheds dust. Each impact gives ONE sharp violet flash. Open palm to hold, fist to crush together, push to throw, palm on the ground for the shockwave. The energy stays on her hands and never recolours her hair or clothes.
CONTINUOUS STORY
00:00-00:03.5 — BREAKOUT
Start in motion: she bursts backward out of the dark store doorway, facing inside, as a zombie's hand grabs her wrist from the darkness. She twists free and falls onto the asphalt. Low wide shot: TWO zombies vault over the hood of CAR B toward her and land heavily. She scrambles back on her hands until her back hits the first fuel pump.
00:03.5-00:07 — FROZEN IN THE AIR (zombie 1)
The zombie from the store follows her out and leaps at her face. She throws up ONE open palm; violet sparks explode into smoke and arcs around her forearm, and the zombie freezes in mid-air 1 metre from her face. Close-up: looking at it, her fear turning cold, she says quietly: "Not today." She flicks her wrist; the zombie flies 10 metres back into the store wall, cracks the stucco and drops.
00:07-00:10 — HEAD TO HEAD (zombies 2-3)
She rises to her feet. The TWO zombies who vaulted CAR B rush her from left and right. She clenches her fist; both are jerked toward each other, collide head to head with a dull thud and fall.
00:10-00:15 — BARREL VOLLEY (zombies 4-7)
She walks out to the edge of the canopy. FOUR zombies stagger toward her from the road. She spreads both arms: the FOUR barrels rise together and hang in a row at chest height, glowing violet. She pushes both palms forward in ONE motion; all four barrels fly at once and knock all FOUR zombies flat, clanging and rolling. She stays at the canopy edge, CAR A 3 metres to her right, breathing hard: a tight group of SIX zombies runs out from behind CAR D toward her, and ONE more crawls to the edge of the canopy roof above her.
00:15-00:20 — THE CAR (ONE continuous shot, zombies 8-13)
Three-quarter wide shot keeping her boots, CAR A and the zombies in frame: she plants her feet and raises both hands, and CAR A lifts off the ground, glowing violet; the wheels hang loose, sand and rust pour from its underside, and the asphalt cracks under her boots. The car rises to 3 metres in the open air outside the canopy. She swings both arms in a flat arc across her front; the car sweeps through the group and knocks all SIX zombies off their feet, then lands on its roof in the open lot, rolls once and stops on its side, glass bursting out.
00:20-00:23.5 — DOOR SHIELD (zombie 14)
The zombie on the canopy roof leaps down at her from 5 metres. In the same moment she jerks her hand toward CAR C; its driver's door rips off its hinges with a metal shriek and stops 1 metre in front of her, upright, as a glowing violet shield. The falling zombie slams into the door and bounces onto the asphalt; she pushes forward and the door drops flat on top of it, pinning it. In the background, FOUR zombies come out of the store doorway.
00:23.5-00:27.5 — SHOCKWAVE AND VORTEX (zombies 15-18)
The FOUR zombies from the store surround her at arm's length. She drops into a crouch and slams one palm onto the asphalt: a low ring of violet light and air distortion bursts outward and throws all FOUR zombies 5 metres away onto their backs. As she stands, broken glass, sand and small debris rise around her into a glowing violet vortex at waist height. She opens her hand and everything drops at once.
00:27.5-00:30 — WALK AWAY
Medium side shot: she turns her head toward the defeated horde, face in clear profile, and says flatly: "Stay down." Wide shot from behind: she takes a few steps away down the empty road past CAR A lying on its side, pink backpack and platform boots clearly visible, violet smoke fading from her fingers, the ruined skyline ahead.
DIALOGUE
Two short lines in English, calm and low, never to the camera: "Not today." at 00:05 to the frozen zombie, "Stay down." at 00:28 in profile to the defeated zombies. No other speech.
SOUND
Natural and event-driven: glass crunching at the doorway, zombie groans and snarls, her fast breathing, feet landing on the car hood, a deep rumble and electric crackle as the energy appears, a low hum while she holds objects, the thud against the store wall, the double thud of the collision, four barrels clanging, the car's metal groaning, sand pouring, the crash and glass bursting, the door ripping off its hinges and the zombie slamming into it, a heavy low boom for the shockwave, the rush of the vortex and glass falling, wind and her footsteps at the end. No music, no narration.
ESSENTIAL CONTINUITY
- Order: breakout, frozen zombie, collision, barrel volley, car, door shield, shockwave and vortex, walk away.
- EIGHTEEN zombies total: 1 from the store, 2 car vaulters, 4 from the road (barrels), 6 from CAR D (car), 1 from the canopy roof (door), 4 from the store doorway (shockwave). Each is knocked down ONCE and stays down. No other zombies appear.
- She never touches lifted objects or zombies with her hands. Lifted objects have real weight and gravity, no clipping; CAR A never hits the canopy, pillars or pumps.
- The store wall stays cracked, the barrels stay scattered, CAR A stays on its side, the door from CAR C stays on the pinned zombie.
- Violet energy only on her hands and forearms, on held objects, in impact flashes, in the shockwave and in the vortex.
- Preserve her face, hair, outfit and footwear exactly as in Image1 throughout.
No slow motion, teleportation, duplicated people, flying heroine, extra dialogue, talking to camera, changing outfits, changing hair colour, lost backpack, extra limbs, distorted hands, guns, blood, gore, explosions, fire, cartoon or anime style, captions, subtitles, readable signs, watermarks.
#zombies #aivideo
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
She looks human. She just jumped 10 floors and came back up.
Created by Seedance 2.5 on @makeugc
Full prompt below 👇
FORMAT
18 seconds, vertical 9:16. One continuous handheld take, real time, no cuts. Photorealistic accidental eyewitness footage of an impossible stunt by a female android in a giant shopping mall atrium, filmed by a spectator on the upper gallery.
LOOK
Ultra-detailed, true-to-life imagery with Hollywood-level realism: real skin pores, fine hair strands, fabric weave, brushed metal micro-scratches, accurate daylight, reflections and shadows. Over this, a DV 16mm tape camcorder handheld feel: subtle fine 16mm-like grain, light MiniDV tape texture, mild chroma bleed, auto-exposure breathing, restrained highlight bloom from the dome, natural motion blur. The texture is a light layer that never hides detail, anatomy or architecture. No heavy degradation or fake vintage filter.
Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. The operator reacts to events instead of anticipating them. Errors are brief and physically plausible. No gimbal smoothness, no drone moves.
The camcorder and camera operator never appear on screen: not in glass reflections, shadows, screens or foreground. No camera body, no hands, no REC symbol, timestamp, subtitles or borders.
REFERENCES
Photo of the android woman: exact face, hair, body, outfit and exposed mechanical waist core. Identity stays locked in every frame.
"seedance_2_video 1 17.58.51.mp4": mall atrium design, extreme multilevel depth, trampoline placement, rebound and somersault trajectory. Current instructions override conflicting details.
CHARACTER
A photorealistic female android nearly indistinguishable from a human: long straight dark brown hair with a center part, light olive skin, dark brown eyes, defined brows, calm confident face. Fitted teal short-sleeve cropped t-shirt, high-waisted black biker shorts ending mid-thigh, plain black athletic sneakers.
Her midriff between shirt hem and waistband is an exposed mechanical core: brushed steel plates, vertical chrome pistons, a central steel panel with two small glowing blue displays, cables and joints lit by internal cobalt light. The glow spills onto the shirt hem and waistband and brightens with exertion.
She moves like an elite gymnast with tiny machine precision: crisp stops, no tremor. She is much heavier than a human, and every contact shows that weight. Hair and clothing behave naturally and stay secure. The core never changes shape, size or position.
ENVIRONMENT AND GEOGRAPHY
A colossal circular mall atrium: white curved structural bands, about ten stacked gallery levels, continuous glass balustrades with steel top rails, storefronts, escalators, a huge glass dome in soft daylight. Hundreds of spectators on every level, filming on phones.
Starting level order, always: CROWD / CONTINUOUS GLASS BARRIER / WOMAN ON NARROW EXTERIOR STONE LEDGE / OPEN DROP.
The ledge is a narrow strip of pale travertine about 40 cm wide outside the glass. The glass is always directly behind her heels. The ledge keeps this width and surface for the whole video. The glass has no gaps, doors or missing panels.
On the ground floor stands exactly ONE large round trampoline: blue padded rim, black bed, steel springs and legs. A cleared 6-meter circle of bare floor surrounds it, ringed by black stanchions with belts. Ground spectators stay behind that ring. The trampoline is not visible in the opening frame.
The drop is real architecture: true floor heights, people and storefronts at believable scale on every level. No lens trickery, no raised floor, no platform under the trampoline.
PHYSICS RULE
Her return to the top is possible only because her leg actuators fire at the instant of trampoline contact, adding thrust through the bed. All launch energy is delivered at that single contact. No mid-air boost, no hovering, no jets, no stretched flight time. Gravity stays real throughout.
CAMERA
The operator stands on the starting gallery behind the glass, about three meters to her side, filming diagonally over the top rail. Opening: tilted, slightly too-tight framing that cuts off the top of her head, then a clumsy correction to full body.
At the jump, react a fraction late, then tilt steeply down after her. One clumsy zoom-in during the fall that overshoots, then eases back wide before trampoline contact so the full depth stays readable. A brief focus hunt on the rail glass resolves back to her.
During the ascent and somersaults, follow upward unevenly but keep her full body framed against the galleries. The camera never points above her head into the dome.
At landing, settle on her full body including both feet. Final beat: a slight face crop, then an imperfect correction.
TIMELINE
0.00-2.40 BOOT-UP.
She stands upright on the ledge, turned three-quarters toward the crowd. Her core powers up: the two blue displays flicker, then lock bright. Ankle and knee servos make a short calibration whir as she shifts weight from foot to foot with mechanical precision. She glances down into the void, then back at the crowd. Spectators murmur, phones go up, someone shouts "Is she real?!"
2.40-4.40 THE SALUTE.
She faces the crowd fully, brings her right hand up in a crisp, exact military salute, holds it for one still beat with a faint confident smile, then snaps the hand down with a tiny servo click. The galleries roar.
4.40-5.60 THE JUMP.
She turns to the void, sets both sneakers at the ledge edge, bends her knees, swings both arms back and launches outward in a deliberate, powerful swan dive, arms spread, body arched. Stone grit puffs from the ledge edge under her push. The operator gasps and tilts after her a beat late.
5.60-8.30 THE FALL.
Real-time free fall, accelerating under true gravity. Gallery levels rush past behind her, spectators on lower levels lean out and point, and she shrinks dramatically in frame. Hair streams upward. Halfway down she tucks, rotates forward half a turn and opens feet-first, arms out for stability, eyes locked on the target. The trampoline and the cleared circle are revealed below during the tilt.
8.30-8.90 THE IMPACT.
Both sneakers hit the exact center of the bed. Under her heavy machine body, the bed plunges almost to the floor, springs stretch to their limit, the steel legs flex. At maximum compression her core flares bright blue and her leg actuators fire with a deep hydraulic thump. One spring snaps off the frame and skitters across the floor. Ground spectators flinch back behind the stanchions. One contact, normal speed, no freeze.
8.90-11.60 ASCENT AND TWO BACKFLIPS.
She rockets upward, galleries rushing downward past her. Near the top of her climb she tucks tightly and completes TWO clean, compact backward somersaults, shoulders, hips and knees coherent, full body visible, the blue core tracing a faint motion-blur arc. The rising speed bleeds off naturally at the apex just above the original ledge. Every gallery erupts in screams and cheers.
11.60-12.40 POWER LANDING.
She opens out, drops onto the narrow ledge and lands in a controlled three-point superhero landing: both sneakers flat and fully supported, one knee deeply bent, the other knee low, right fist pressed onto the stone. A heavy metallic impact. A hairline crack spreads a short distance through the travertine under her fist, and a small puff of stone dust lifts. The glass behind her shudders and rings but stays intact. Her hair swings forward, then settles. Perfectly stable, no wobble, no slip.
12.40-15.40 THE RISE.
She holds the pose for one breath. The core glow pulses down to calm. She rises slowly and smoothly to full height with a soft hydraulic hiss, brushing grit off her knuckles with her thumb. The crowd goes wild: people pound the rail, scream, film, some cover their mouths. The operator's framing shakes with excitement but keeps her whole body.
15.40-18.00 FINAL SALUTE.
She turns toward the crowd, close to the operator's direction but never into the lens, and gives a sharp two-finger salute from her brow with a small cool smirk. The frame briefly crops her forehead, then corrects. End on her standing tall and still on the cracked ledge, blue core glowing, crowd cheering behind the glass.
AUDIO
Authentic camcorder microphone: close crowd voices, huge mall reverb, auto-gain pumping, brief clipping only on the loudest roars. Servo whir at boot-up, a tiny click after the salute, rushing air during the fall, a deep hydraulic thump and a heavy elastic boom at impact, a metallic ping of the snapping spring, swelling cheers, a heavy metal-on-stone landing crack, ringing glass, a soft hydraulic hiss as she rises. She stays silent. All intelligible speech in English. No music, no voice-over.
CONTINUITY
One android woman, one trampoline, one salute at start, one intentional jump, one trampoline contact, one actuator thrust, two backflips, one stable landing, one final two-finger salute. The snapped spring stays on the floor. The crack stays in the ledge after landing. Ledge width, glass, crowd positions, trampoline, light, outfit and core remain consistent.
NEGATIVE CONSTRAINTS
No push, no slip, no hanging from the ledge, no fall after landing. No wide slab instead of the narrow ledge, no glass gaps, no body through glass, no shattered glass. No crowd inside the cleared circle, no extra trampoline, no early trampoline reveal. No mid-air thrust, hovering, slow motion or speed ramps. No camera pointing into the dome, no morphing anatomy, no changing mechanical parts, no cartoon, plastic or video-game CGI look, no visible camera or operator, no camera-facing dialogue.