AI Video Creator • Tester • AI Tools Expert Partner: @makeugc
Joined March 2026
- Tweets2K
- Following463
- Followers4.9K
- Likes5.3K
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
Seedance 2.5 vs Kling 4.0: is better realism worth 16× the price? 👀
Same prompt. Side by side. Both made on @makeugc
My take:
1) Seedance looks more realistic, but Kling isn’t far behind.
2) Both followed the instructions well. But Seedance took 3 attempts to get a clean result. Kling got it right on the first try.
3) Kling is ≈16× cheaper.
For pure quality, Seedance is still the clear winner for me. But once I factor in time, money and retries, I can’t call it the obvious choice.
Kling is a solid, much cheaper alternative. Try the same prompt and see which you prefer.
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
🤖 Made with AI
I put Seedance 2.5 and Wan 3.0 head-to-head with the same prompt after seeing Wan ranked above Seedance by Artificial Analysis
I used the same fitness vlog prompt with both models on @makeugc
Wan followed the instructions well, but Seedance looks much more natural to me. With Wan, I still get that obvious “AI video” feeling.
Personally, I think Wan’s only real advantage is its lower price. In terms of quality, it falls short.
What do you think? Which one would you pick?
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
Now you can recreate any viral video in 3 simple steps 👇
Use Seedance 2.5, Wan 3.0 or Kling 4.0 on @makeugc
1. Find a viral video or simply a clip you like.
2. Upload it as a video reference and select the SAME duration as the original. This part matters.
3. Ask the model to preserve all the original movements, then describe what you want to change: the character, clothing or location. You can attach your own image references too.
I even changed this one from vertical 9:16 to horizontal 16:9.
Done. Your own take on the original, ready to post.
#AIVideo
🤖 Made with AI
Can AI get any more realistic than this? 🤯
Made this with Seedance 2.5 on @makeugc using Alpha Mom’s exact prompt.
PROMPT 👇
**CAMERA:**
DV 16mm tape camcorder handheld feel. MILA films the opening and closing selfies herself; her gym friend films the dumbbell exercises handheld. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder and camera operator never appear 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 effort mixed with humor. Quick, casual cuts between excerpts from an ongoing workout. Exercise shots begin and end mid-set, with continuous rhythmic repetitions at normal speed. She talks while moving, without stopping to pose. Time passes between clips; equipment setup and camera handoffs happen off-screen.
**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.
**Setting**
A gym dumbbell area in the evening — weight racks, benches, soft overhead lighting. Two other gym-goers exercise casually in the background, away from MILA. An angled mirror naturally reflects her back, blue shorts and legs in wider shots. She uses the same matching pair of small black hex dumbbells throughout.
**Storyboard (15s, 6 shots)**
1. *(0–2.5s, moving arm’s-length selfie)* Already walking past the weight rack, MILA smiles toward the lens and briefly glances at the equipment. Her face and blue sports bra are visible; the framing bobs with her footsteps. MILA: “Arm day. This should be quick.”
2. *(2.5–5s, handheld medium shot)* Cut into an ongoing set of standing alternating dumbbell curls. One arm rises as the other lowers; she keeps the rhythm while speaking. The camera drifts slightly with the operator’s movement. MILA: “These felt lighter yesterday.”
3. *(5–7.5s, handheld wider three-quarter shot)* Another excerpt: MILA is already doing lateral raises, repeatedly lifting and lowering both dumbbells without holding a pose. Her rear view is visible in the mirror. MILA (breathless): “I picked the light ones!”
4. *(7.5–9.5s, handheld close-up insert)* Her hand and forearm grip a dumbbell through the continuing repetitions. The camera briefly loses focus as the weight moves, then catches it again. No dialogue — breathing and distant gym sounds.
5. *(9.5–12s, handheld medium-wide shot)* MILA walks briskly past the camera toward the rack, carrying both dumbbells beside her thighs. The operator turns to follow her as she laughs. MILA: “Yep — my arms just quit.”
6. *(12–15s, arm’s-length selfie after the set)* A clear jump cut: the dumbbells have been returned, and MILA is already holding the camera herself. Walking out of the weights area, she shakes out her free hand and grins. MILA: “Same time tomorrow? No promises.”
#AIVideo
Seedance 2.5 vs Kling 4.0: is better realism worth 16× the price? 👀
Same prompt. Side by side. Both made on @makeugc
My take:
1) Seedance looks more realistic, but Kling isn’t far behind.
2) Both followed the instructions well. But Seedance took 3 attempts to get a clean result. Kling got it right on the first try.
3) Kling is ≈16× cheaper.
For pure quality, Seedance is still the clear winner for me. But once I factor in time, money and retries, I can’t call it the obvious choice.
Kling is a solid, much cheaper alternative. Try the same prompt and see which you prefer.
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
🤖 Made with AI
I put Seedance 2.5 and Wan 3.0 head-to-head with the same prompt after seeing Wan ranked above Seedance by Artificial Analysis
I used the same fitness vlog prompt with both models on @makeugc
Wan followed the instructions well, but Seedance looks much more natural to me. With Wan, I still get that obvious “AI video” feeling.
Personally, I think Wan’s only real advantage is its lower price. In terms of quality, it falls short.
What do you think? Which one would you pick?
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
Life looks better in color.
Seedance 2.5 on @makeugc
A little surrealism, a little magic, and a world full of color.
PROMT:
A 20-second vertical 9:16 surreal fashion film. Use the attached reference image as the style and character reference (the woman, the mint striped sofa, the teal river, the flower hills, the planet). One stylish woman with a platinum-white pixie cut travels through a dreamlike pastel landscape of flower-covered mountains: she drifts down a teal river on a striped sofa, rides a floral-patterned unicorn, drives a striped flower-decorated convertible and cycles away along a winding teal road. The video starts already in motion and ends on a wide shot of her riding toward the mountains under one floating ringed planet.
MAIN SUBJECT
One adult woman in her late 20s, athletic slim build, fair skin, calm editorial expression. Sleek platinum-white pixie cut, round gold-rimmed sunglasses with dark lenses, matching red-and-cream vertical-striped jacket and trousers in thick opaque cotton with a tailored cut, cream flat shoes. The same outfit, hair and sunglasses in every shot.
LOCATION
Fully fantastical dreamscape, not a real place. Foreground: giant decorative flowers about 2 metres tall (yellow dahlias, red poppies, white calla lilies). Middle ground: rolling hills carpeted with millions of tiny pink, white and violet blossoms, a deep teal sparkling river and a winding deep-teal road. Far background: towering mountains about 300 metres high with a soft porous sponge-like surface in peach, lavender and butter-yellow. Pale turquoise clear sky with ONE large lilac ringed planet hanging above the mountains, always in the same place.
CONTINUOUS STORY
00:00-00:05 SOFA ON THE RIVER
Opens already in motion. Medium-wide three-quarter shot at low eye level. A vintage two-seat sofa upholstered in mint-and-cream vertical stripes with tangerine-lacquered armrests floats like a boat on the teal river, its base about 10 cm under the surface, small ripples spreading around it. She sits upright with legs crossed, one hand holding a long flower stem, the other resting on the armrest. The river carries the sofa slowly toward the camera and to the right. At 00:03 she slowly turns her head toward the camera. At 00:04 a giant yellow dahlia in the foreground sweeps across the lens and wipes the frame.
00:05-00:10 UNICORN ON THE RIVER BANK
The dahlia wipe reveals a side tracking medium-wide shot, camera moving left to right at the same speed as the animal. She rides a graceful pearl-white unicorn with a spiral horn, a mane and tail of yellow and orange flowers, and a body painted with floral patterns in tangerine, teal and yellow. A flower garland serves as reins. The unicorn canters through shallow water along the bank: each stride a hoof strikes the water, a spray arc lifts, the hoof lands. Her body rises and settles with the rhythm, one hand on the mane, the other holding the garland, her pixie cut barely moving.
00:10-00:15 STRIPED CAR
Medium close-up tracking shot alongside the car, the car moving left to right. She drives a vintage open-top convertible in mint-and-cream stripes with tangerine chrome bumpers and garlands of flowers on the hood and doors. Both hands on a thin cream steering wheel, her face and hands visible. The car rolls on smooth teal asphalt along the winding road between flower hills, wheels turning, petals blowing backward, her sunglasses catching the sun.
00:15-00:20 BICYCLE FINALE
Three-quarter rear tracking shot that slowly pulls out to a wide shot. She cycles a pastel peach-and-lavender vintage bicycle with a woven basket of flowers along the same winding teal road toward the gap between two giant mountains. Pedals turn, striped trouser legs pump, cream shoes on the pedals, both wheels spin forward, the basket sways slightly. At 00:18 she glances over her shoulder at the camera with a confident smile, then faces forward again.
#surrealism
#aiart
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
POV: you went for a late swim
Seedance 2.5 on @makeugc. I just wanted to test how real it looks.
Now I can't unsee it 💀
Would you feed them?
Prompt:
Real amateur iPhone video, vertical, filmed handheld at night by someone crouching at the edge of a hotel swimming pool at 2am, the phone held low at water level. Harsh direct phone flash mixed with the turquoise glow of the underwater pool lights, shaky handheld camera, auto-exposure flicker, visible digital noise and grain, slight motion blur, candid unedited footage, no cinematic color grading, looks like a real video posted on social media. From the very first frame, two beautiful young women with long wet hair and realistic skin texture, wearing bikini tops, are in the water right next to the pool edge, laughing hysterically with slightly unhinged energy, and behind them their large realistic fish tails with wet iridescent scales and fins slap and flick out of the water, clearly visible under the flash. They push closer to the camera and rest their elbows on the wet tiles, faces almost touching the lens, giggling. The filmer's hand enters the frame holding a few pieces of sushi on the open palm; the two mermaids snap at the sushi with their mouths like playful seals, competing for it, one steals a piece from the other, both chewing and laughing with their mouths full, grains of rice stuck to their lips and cheeks. Then one of them excitedly slaps her tail on the water and a big splash hits the camera, water droplets on the lens, both laughing loudly. Real physics of water and wet hair, natural sounds only: splashing, laughter, giggles, no music.
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
Imagine holding her coffee while she tells the internet you don’t exist.
Made with Unlimited Seedance on @makeugc
Prompt👇
Create a native 15-second, vertical 9:16 real street-interview video: one continuous handheld take with no cuts, filmed by a camera operator on a city sidewalk in daylight. It must look exactly like a real viral man-on-the-street interview clip: an off-screen interviewer holds a fuzzy microphone to a young woman's face, she says she is very single, and the camera slowly pans to reveal her boyfriend standing right beside her, holding her bag and her coffee. No reference image.
CORE RULES
Two adults in focus: MAYA, a woman of 25, and LIAM, her boyfriend, a man of 27. The interviewer is never seen except his RIGHT hand and the sleeve of his plain black jacket holding the microphone; his voice comes from off-screen. One continuous shot from the first frame to the last, no cuts. Each person keeps the same face, hair, body and outfit throughout. Each has exactly two arms and two legs; each hand has five fingers; joints bend only naturally. The recording camera is never visible. Natural, understated behaviour: nobody performs for the camera. Fluid real-time motion, no freezes, no slow motion. No readable text, numbers, logos or brand marks anywhere, including on the microphone, the cups, the bag, clothing and shop signs.
CHARACTER
Tone: a real street interview that turns into a disaster in one second. Funny because it is real.
MAYA is a beautiful, eye-catching 25-year-old woman, naturally sexy in an effortless, believable way. She has a curvy, athletic figure with a full, large, natural-looking bust, a defined waist and realistic body proportions. Long dark-brown hair worn down in soft loose waves, never across her face. She wears a fitted white ribbed crop top with a softly scooped neckline under an open oversized light-blue denim jacket, high-waisted dark jeans and small gold hoop earrings. Fresh glowing everyday makeup: defined brows, soft mascara, nude lip gloss. Confident, flirty, a little sassy. The clip stays about her face and the moment, never about her body. No logos.
LIAM is a 27-year-old man, sweet and ordinary: short messy dark-blond hair, light stubble, slim build, average height. He wears a plain navy hoodie and plain grey trousers. A small pastel-pink leather shoulder bag with a thin strap hangs on his LEFT shoulder the whole clip. He holds two plain white paper coffee cups with plain white lids, one in each hand. No logos.
FACE
MAYA: oval face with high cheekbones, almond-shaped warm brown eyes with long dark lashes, defined natural brows, full lips with nude gloss, small mole above the LEFT corner of her upper lip, straight natural white teeth, warm olive skin with a healthy glow. Flirty and confident, then frozen with a tight, forced smile, then eyes closed and lips pressed in regret.
LIAM: narrow face, hazel eyes, light stubble. A warm, happy smile that freezes, then a flat, blank, hurt look.
Both: eyes focus on what they look at, gaze moves before the head, natural blinking, gradual expressions, head turns under 45 degrees. Nothing covers either face. When they speak, mouths open moderately, lips close on m, b and p; smiles show only upper teeth. No cartoonish faces, no glassy eyes, no warped teeth.
VOICE
MAYA: warm, playful, slightly husky, soft American accent, natural pace, a smile in her voice; her last line is quick and strained. LIAM: calm, flat, quiet, American accent, one short line. INTERVIEWER (off-screen male voice): friendly, upbeat, close to the microphone, slightly louder. All recorded by the same handheld microphone: clear voices, light street ambience, soft wind rustle on the mic. Every word matches the speaker's lips. Each line is said once.
CAMERA
CAMERA:
Authentic casual footage captured with an older consumer digital camera. Handheld DV 16mm camcorder aesthetic. An unseen person operates the camera from a plausible nearby position. Preserve the viewpoint, framing and shot sequence described in the scene. Camera reactions feel human and slightly imperfect. The recording device stays outside the frame.
The operator stands about 1.2 metres in front of MAYA at her eye level. From 0 to 8.8 s the frame shows MAYA from the waist up, slightly left of centre, with the microphone in the lower-left of the frame; at the very right edge of the frame, part of a navy hoodie sleeve and a white coffee cup are sometimes visible. From 8.8 s to 10.3 s the camera slowly pans about 25 degrees to the RIGHT, without moving forward or zooming, to reveal LIAM standing about half a metre to MAYA's LEFT side (screen right); from 10.3 s to the end both are in frame from the chest up: MAYA on the left, LIAM on the right.
CAMERA HAND
The camera operator is never seen. The interviewer's RIGHT hand and black sleeve enter from the bottom-left edge of the frame and hold the microphone below MAYA's chin the whole time, even during the pan.
HANDHELD
HANDHELD:
Natural hand shake, slightly crooked framing and small framing corrections. Brief motion blur during camera movement, occasional delayed autofocus after reframing and subtle vertical movement from the operator's body. Keep faces and important actions readable. Avoid perfectly stabilized or gimbal-like movement.
LOOK
LOOK:
Soft digital-tape look with subtle vintage DV character. Soft fine detail, faint digital noise, mild compression, slightly muted colours, restrained contrast and imperfect white balance. Preserve natural skin tones, pores, wrinkles, fabric texture and realistic surface reflections. No beauty filters, plastic skin, glossy commercial finish or heavy colour grading.
LIGHTING
LIGHTING:
Natural overcast daylight from a pale cloud-covered sky. Soft shadows, gentle light falloff, ordinary skin tones and realistic surface reflections. Keep faces and surroundings clearly exposed while preserving natural differences in brightness. No sunset tint, dramatic rim lighting or artificial glow.
VISUAL MATCH
The image must look exactly like a real viral street-interview clip: handheld, eye level, slightly tight framing, a big fuzzy grey microphone windscreen in the lower-left corner, ordinary overcast city light, everything readable, no grading, no shallow blur, the autofocus breathing a little during the pan.
SETTING
A busy city sidewalk on an overcast afternoon. Behind MAYA: a row of shopfronts with plain awnings and blank signs, a bus stop shelter, a few parked cars, trees with pale leaves. The pavement is grey and slightly damp. Shop windows show no reflections of the crew. Far behind, two ordinary passers-by walk past once, about 8 metres away, never looking at the camera, never coming closer. The microphone has a plain grey fuzzy windscreen and a plain black handle, no flag, no text.
BACKGROUND
Readable instantly as a city street. Three layers: the fuzzy microphone in the near lower-left foreground; MAYA and LIAM in the middle; the shopfronts, bus stop, cars and passers-by behind. Palette: grey street, white top, light-blue denim, navy hoodie, the pastel-pink bag as the only bright accent. Background life: one cyclist passes far behind at 3.0 s. Background story: before the pan, at 3.5 s and again at 6.5 s, a navy hoodie sleeve and a white coffee cup drift into the very right edge of the frame and back out, as if someone is standing right next to her waiting. The background never warps.
MOTION
Real human motion with weight. MAYA speaks with small head tilts and expressive brows, shifts her weight once from her RIGHT foot to her LEFT at 5.0 s. LIAM stands still, then extends his RIGHT arm with a coffee toward her, then freezes. Eyes lead, then head, then shoulders. Left and right sides never mirror. No freezes except the deliberate frozen moments, no slow or sped-up motion, no posing.
DEFECT PREVENTION
Hands: the interviewer's RIGHT hand grips the microphone handle the whole clip, five fingers wrapped around it. MAYA's hands stay relaxed at her sides out of frame except once: at 2.8 s her LEFT hand tucks a strand of hair behind her LEFT ear in one 0.6-second motion and drops back down; she never touches her face again and never takes the cup. LIAM holds exactly two coffee cups: his RIGHT hand holds one cup, which he extends toward MAYA from 8.5 s and slowly lowers to his side at 13.5 s; his LEFT hand holds the second cup in front of his chest the whole time. Five fingers per hand; fingers never merge with the cups, the microphone, the bag strap or the body.
Face: both faces stay visible whenever they are in frame; the microphone stays below MAYA's chin and never blocks her mouth; LIAM's cups stay below his chin. MAYA's forced smile is tight and small, not a grimace. Head turns under 45 degrees.
Body and legs: both stand still on the pavement with feet planted the whole clip. LIAM is standing beside MAYA from the first frame, just outside the right edge of the frame; the pan reveals him, he never walks in.
Objects: one microphone, exactly two plain white coffee cups with white lids, one pastel-pink shoulder bag on LIAM's LEFT shoulder. Objects never vanish, duplicate, change shape or colour, or pass through bodies. The bag strap stays on his shoulder. No readable text or logos anywhere.
Continuity: one continuous take, no cuts. The camera pans only once, to the RIGHT, between 8.8 s and 10.3 s, at the same distance. MAYA stays on the left after the pan, LIAM on the right. Same outfits, same overcast light.
Physics and environment: a light breeze moves MAYA's hair slightly and rustles the microphone windscreen. No reflections of the crew in windows. Only the two distant passers-by and one distant cyclist appear; nobody else comes near.
STORYBOARD (15 s, one continuous take)
START POSE: The first frame shows MAYA from the waist up, slightly left of centre, the fuzzy microphone already under her chin from the lower-left, a playful knowing smirk, eyes narrowed, hair moving slightly in the breeze. LIAM is out of frame on the right.
00:00.0-00:02.0 - INTERVIEWER (off-screen, upbeat): "Quick one. Are you single?" FACE MAYA: brows lift, the smirk widens, eyes flick up and to the side.
00:02.0-00:03.8 - MAYA (flirty, confident; not loud): "Oh, VERY single." At 2.8 s her LEFT hand tucks a strand behind her LEFT ear and drops. FACE: a playful smile with upper teeth.
00:03.8-00:05.5 - INTERVIEWER (curious): "What's your type?" At 3.5 s a navy sleeve and a white cup drift into the right edge of the frame and back out. FACE MAYA: eyes go up thoughtfully.
00:05.5-00:08.3 - MAYA (sure of herself, teasing; not smug): "Tall, funny, NOT clingy." She gives a tiny head shake on "not". At 6.5 s the sleeve and cup drift into the right edge again.
00:08.3-00:08.8 - LIAM's RIGHT hand with a coffee cup reaches in from the right edge toward MAYA.
00:08.8-00:10.3 - The camera slowly pans to the RIGHT and reveals LIAM right beside her: average height, the pastel-pink bag on his LEFT shoulder, one cup held out toward her in his RIGHT hand, the second cup in his LEFT hand at his chest, a warm happy smile. His smile freezes as he realises what he just heard.
00:10.3-00:12.0 - MAYA freezes; her eyes go to the lens. MAYA (quick, strained, through a tight forced smile): "He's my COUSIN."
00:12.0-00:13.5 - LIAM slowly turns his head about 40 degrees to look at her. LIAM (flat, quiet, blank; not angry, not loud): "Since WHEN?"
00:13.5-00:15.0 - MAYA closes her eyes and presses her lips together. LIAM slowly lowers the extended cup to his side, still looking at her. The microphone hangs in the air.
SOUND
Real street-interview audio through the handheld microphone: light city ambience, distant traffic, a bus hissing far away, soft wind rustle on the windscreen, the interviewer's two lines close to the mic, MAYA's lines, her small flirty laugh, a beat of silence after the reveal, LIAM's flat line, a faint street sound under the final silence. No music.
HANDS AND FEET
Five fingers on each hand, never merging with each other, the microphone, the cups, the bag strap or the body. Nobody touches their face except MAYA's one hair tuck at 2.8 s. Exactly two arms and two legs each; both stand with feet planted.
CONTINUITY AND REALISM
One continuous take. Two people, an off-screen interviewer's hand and microphone, two coffee cups, one pink bag, a few distant passers-by, all consistent from start to end. No floating or disappearing objects, no transformations, no captions, logos or watermarks. The framing stays on faces and reactions, never on her body. Everyone is an adult.
FINAL FEEL
A real viral street interview where a girl says she is very single and not into clingy guys, and the camera finds her boyfriend right beside her holding her bag and her coffee. Real, imperfect, handheld. Not a commercial. Not a fashion shoot. Not polished influencer content.
Alpha Mom retweeted
She was the calmest robot at the expo. For about 4 seconds.
Made with Unlimited Seedance on @makeugc
Prompt👇
Create a native 15-second, vertical 9:16 handheld iPhone video filmed by a person standing in a crowd at a tech expo booth. One continuous shot, no cuts. The uploaded image is the exact first frame of the video.
REFERENCE IMAGE LOCK
The android girl in the center of the image is NOVA. Keep her 100 percent identical to the image in every frame: the same face, facial features and proportions, the same light hazel eyes, brows, lips and skin tone, the same jet black hair with center part, the same teal crop T-shirt, the same high-waisted black bike shorts with silver buttons, the same body shape, and the same exposed mechanical waist band with silver pistons, springs and servos. Do not redesign, beautify, age or slim her. Keep the same booth, crowd, ceiling, light, colors and camera angle as in the image.
The spectator hand holding sunglasses on the LEFT edge lowers out of frame within 0.5 seconds and never returns. Nova wears no sunglasses in the entire video.
CORE RULES
One continuous handheld shot. One main character: NOVA. Nova stays on the same spot for the whole video: she never walks, never turns around, never spins. From 00:04.0 there is an empty circle of at least 3 meters around her; nobody is within 3 meters of her while she moves. She never touches anyone. Exactly two people fall, and they fall from fright at the loud spark crack, while Nova is still standing frozen and not moving. Nobody falls while Nova is striking. Everyone else stays standing for the whole video. Nobody is injured. No text, captions or overlays on screen. All people are adults aged 18 to 30.
CHARACTER
NOVA looks exactly like the image: a female android who looks like a real young woman, apparently 23 years old, slim, very narrow waist, full, large, natural-looking bust, long athletic legs, realistic body proportions. Straight glossy jet black hair, center part. Fitted teal short-sleeve crop T-shirt, high-waisted black bike shorts with a row of small silver buttons, black sneakers.
THE ROBOT WAIST: exactly as in the image, a fully exposed band between top and shorts with brushed silver steel actuators, vertical pistons with coil springs, small servo motors, black cables and aluminium plates. Always visible, never changes shape. In fight mode tiny blue status lights blink inside it.
FACE
Identical to the image in every frame. Normal mode: sly closed-lip half smile, eyes open and on the camera; she never looks down. Fight mode: blank, emotionless machine face, eyes locked on the camera, lips closed. Only upper teeth if teeth show. Her face is always sharp and never motion blurred. Her hair never covers her face.
VOICE
Soft, calm, slightly synthetic female voice with a small digital edge. One line only, at the end.
CAMERA
Held by a spectator about 2 meters in front of Nova at chest height, pointing slightly down, as in the image. At 00:04.0 the camera person steps back about 1.5 meters once, so Nova is visible from head to feet inside the empty circle with the crowd around, and stays there to the end. A young woman in a denim jacket holding a black tablet is on the RIGHT edge at the start.
CAMERA HAND
The phone holder is never visible.
HANDHELD
Natural small shake in the calm part, a strong jolt at the spark crack, then a slightly nervous shake that keeps Nova centered. No zoom.
LOOK
Plain iPhone video at 60 fps, default phone processing, light sharpening, natural noise, no filters, no color grading. Real documentary feel.
LIGHTING
Even overhead light from rows of round LED ceiling lamps in a large exhibition hall. Neutral cool white, soft shadows, her face always well lit.
VISUAL MATCH
The image must look exactly like the uploaded image: a phone video from inside a dense crowd at a tech expo, neutral grey and white hall, open steel truss ceiling with many round lamps, the teal top as the only strong color accent, black T-shirts with blue lanyards on the crowd, blue panels behind, everyday iPhone sharpness, no overlays.
SETTING
The same robotics booth inside a huge modern exhibition hall during the day.
BACKGROUND
As in the image: about 20 young adults with blue lanyards around Nova, several filming with phones, a metal cart with robot parts behind her, white booth walls, a dark blue backlit poster on the LEFT, a blue flag, steel truss ceiling. T-shirts are plain black with no logos or text. One distant movement: a person walking far behind the booth.
MOTION
Normal mode: human-like but slightly too precise. Fight mode is a malfunctioning robot running a martial arts program: every move is a sharp mechanical jerk that snaps into a pose in 0.15 seconds and then stops dead and holds completely still for 0.4 seconds before the next move, like a robot hitting fixed positions. No flowing dance moves, no swaying, no circling arms. Each snap has a servo click and a whoosh. Hair swings on each snap and settles during each hold.
DEFECT PREVENTION
Hands: Nova's hands are either tight fists with the thumb outside or flat open palms with fingers together, five fingers each, never merging. Every strike goes into empty air in front of her or to her side, never toward a person and never toward the lens. The woman on the RIGHT holds the tablet with both hands until she steps out of frame at 00:03.8. The camera hand is never visible.
Face: identical and sharp in every frame. Her head never jerks or snaps; she always faces the camera, head turns under 20 degrees. Hair never covers her face.
Body and legs: exactly two arms and two legs. Her feet stay on the same spot all video. Every kick uses one leg while the other foot stays flat on the floor carrying her weight; knee up first, then a straight extension forward no higher than waist height, then the foot back down to the same place. No jumps, no spins, no turning her back, no walking. Knees bend only forward over the toes.
People: from 00:04.0 nobody stands within 3 meters of Nova. Exactly two young men end up sitting on the floor, both at the far edge of the circle, at least 3 meters away from her. All other people stay standing for the whole video. Nobody appears from behind Nova.
Objects: one tablet, one metal cart (always behind Nova at 3 meters, untouched). All phones stay in their owners' hands. Objects never vanish, duplicate or pass through bodies. No readable text anywhere.
Continuity: Nova's face, outfit, hair, mechanical waist, booth, LEFT/RIGHT positions and light stay identical through the whole video. Her final pose matches the first frame.
Physics: one spark moment only, a burst of small blue sparks from her waist at 00:03.5. No smoke, no fire. The background never warps.
STORYBOARD
00:00.0-00:02.0 HOOK, FIRST FRAME: exactly the image. Nova faces the camera, sly closed-lip half smile, eyes on the lens, arms along her thighs, robot waist fully visible, crowd filming, chatter. 00:00.0-00:00.5: the hand with sunglasses on the LEFT lowers out of frame. 00:00.5-00:01.3: her smile widens slightly, one slow blink. 00:01.3-00:02.0 STRANGE DETAIL: head and face stay completely still and sharp, smile unchanged. Only her RIGHT shoulder twitches up twice, fast and mechanical, with two sharp electric clicks, and a piston in her waist jerks.
00:02.0-00:03.5 FREEZE: she is too still, smile frozen, eyes not blinking. 00:02.3: her RIGHT arm rises stiffly straight forward to shoulder height, palm flat down, and freezes, rising servo whine. 00:02.9: her LEFT arm rises the same way. Her smile switches off; face blank. The operator on the RIGHT taps the tablet fast. Chatter drops.
00:03.5-00:04.5 SPARK AND PANIC: a burst of small blue sparks pops from her waist with a loud electric crack, blue lights blink inside the machinery. Nova does not move at all, arms still frozen forward. The crowd panics and pushes back hard, opening a wide empty circle around her. The operator ducks out of frame. The camera person jumps back 1.5 meters with a strong jolt. In the push, two young men at the far edge of the circle, one on the LEFT and one on the RIGHT, both at least 3 meters from Nova, lose their balance and drop down sitting on the floor on their backside, hands behind them. They stay sitting on the floor until the end, staring at her. Nova is still frozen and far from them.
00:04.5-00:06.5 SNAP 1: Nova snaps both fists to her hips and drops into a wide horse stance in 0.15 seconds, then holds still. Snap: RIGHT straight punch forward into empty air, stop dead, hold. Snap: LEFT straight punch forward, stop dead, hold. Each with a servo click and a whoosh.
00:06.5-00:08.5 SNAP 2: snap: RIGHT open-palm chop out to her RIGHT side at shoulder height, hold. Snap: LEFT open-palm chop out to her LEFT side, hold, both arms now out to the sides like a T. Snap: both fists back to her hips, hold.
00:08.5-00:10.5 SNAP 3, KICK: weight onto her LEFT leg, RIGHT knee snaps up to waist height, hold 0.3 seconds, the leg snaps straight forward into a front kick into empty air at waist height, stops dead, hold 0.4 seconds, the foot returns to the floor in the same place. Back in the stance. The crowd gasps from a safe distance; the two men on the floor scoot back a little.
00:10.5-00:12.0 FINAL POSE: snap: RIGHT straight punch forward, LEFT fist at hip, stop dead and hold completely still. A fading servo whine. The blue lights in her waist go off. Silence. Everyone frozen with phones up.
00:12.0-00:15.0 PUNCHLINE: she lowers her fist, straightens up out of the stance, feet together, arms along her thighs, exactly like the first frame. Her face switches back to the sly closed-lip half smile, eyes on the camera. 00:12.5-00:14.0 she says calmly: "Sorry. Self defense mode was ON." Slow and playful, stress on ON; not monotone, not shouting. 00:14.0-00:15.0: one slow blink, the crowd bursts out laughing, one man on the floor raises a thumb up.
STAYS STILL: Nova's feet position, the booth walls, poster, cart, ceiling and lights.
SOUND
Busy expo hall ambience and chatter. Two sharp electric clicks at 00:01.3. Rising servo whine at 00:02.3. Loud electric crack and gasps at 00:03.5, then shouting. A servo click and a short whoosh on every snap. Silence at 00:11.0. Her line, then a burst of laughter. No music.
HANDS AND FEET
Fists tight with the thumb outside, open palms flat with fingers together, five fingers each. Supporting foot always flat on the floor. Sneakers stay on. No close-up of feet.
CONTINUITY AND REALISM
Same Nova as the image in every frame, same outfit, same visible mechanical waist, same booth, same light. One continuous take. The crowd behaves like real expo visitors: scared, keeping their distance, then laughing.
FINAL FEEL
Real phone footage from a robotics expo where a lifelike android girl short-circuits into a rigid martial arts program, the crowd panics, two guys end up on the floor, and she calmly apologizes. Not polished influencer content.
Alpha Mom retweeted
What could character switching look like in GTA VI? I decided to experiment with AI and create my own fan concept of switching between Lucia and Jason. Made with WAN 3.0 on @makeugc, using AI-generated gameplay footage and reference images.
I tried to capture that familiar GTA V character-switching feel, but imagined how it could look in Vice City with modern graphics.
Of course, this is just a fan concept, not actual GTA VI gameplay.
What do you think? Would you like Rockstar to keep the classic character-switching mechanic or come up with something completely new?
#aivideo #GTAVI
🤝 Paid partnership · 🤖 Made with AI
Let's have some fun! I made this experimental trailer using WAN 3.0's character replacement feature. Huge thanks to @makeugc for giving us access to all the top AI models!
What if we replaced one of the main characters in GTA VI with someone completely unexpected? Mr. Bean is pretty unexpected, right?
All you need to get a result like this is 3 simple steps:
1️⃣ Upload the original video.
2️⃣ Upload reference images of the character.
3️⃣ Describe in the prompt who you want to replace.
WAN 3.0 understands prompts really well and doesn't require any strict rules or complicated instructions. I've tested it myself!
Would you like to see the full version of the trailer?
#aivideo #GTA6
Alpha Mom retweeted
Adult Haunted House, Episode 1:
"He wasn't scared of anything. Until she showed him her secret "
Made on @makeugc (Seedance 2.5). You can try it for just $1. Prompt and details below 👇
Watch till the end 👀
What should be in the next box?
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
The bear came for the candy. Nobody told him the doll wanted a hug
Made with Unlimited Seedance on @makeugc
Prompt👇
SEEDANCE MASTER PROMPT: "THE DOLL THAT SCARED THE BEAR"
Photorealistic Halloween doorbell-camera incident | Target duration: 23 seconds | One continuous security-camera viewpoint
CORE OBJECTIVE
Generate a highly believable, unexpectedly funny-but-creepy Halloween incident that looks like genuine consumer doorbell security footage accidentally capturing something impossible. The clip must feel observed rather than directed: a real suburban porch at night, a real-looking black bear behaving like a curious wild animal, an ordinary creepy Halloween doll, a bowl of candy, a glass front door, and a homeowner visible behind the glass. The doll's sudden movement is the single main shock. The bear's startled escape is the physical payoff. The final image of the doll holding the homeowner's phone is the quiet, uncanny twist. Keep the action clear enough to understand instantly, with no explanatory dialogue, no cinematic coverage, no dramatic music, and no obvious AI visual artifacts.
The clip should resemble authentic doorbell-camera footage viewed after a motion alert. It must not resemble a polished horror-movie trailer, a music video, a game cutscene, or a sequence of unrelated generated shots. Use one fixed camera, one spatially consistent porch, continuous real-time action, practical night lighting, natural animal movement, and restrained visual storytelling. The camera never becomes a character and never moves to help the audience. The viewer is simply watching a security recording.
FORMAT AND VISUAL LANGUAGE
- Duration: approximately 22-25 seconds.
- Aspect ratio: vertical 9:16 composition, as if exported from a vertical smart doorbell camera. Preserve the full porch action inside this frame.
- Camera: a single fixed, wide-angle doorbell security camera mounted beside the front door, about 1.6-1.8 metres above the porch floor, angled slightly downward.
- Lens: realistic consumer security-camera wide angle, approximately 150-160-degree field of view. Mild edge distortion is acceptable, but do not bend bodies, railings, or door frames unnaturally.
- Recording character: compressed low-light digital footage, subtle sensor noise, slight sharpening, modest compression artifacts, realistic shadow noise, and believable automatic exposure. The image should still be clear enough to read the doll's eyes and the bear's reaction.
- Lighting: a warm porch bulb above the door, a weak spill of indoor light through the glass, and cool ambient darkness beyond the steps. The porch bulb is the main light source. Do not add theatrical spotlights, coloured horror lighting, artificial fog, or glowing supernatural effects.
- Colour: natural night-time colours, muted wood and siding, warm amber near the door, cooler shadows in the yard. Avoid extreme teal-orange grading, crushed blacks, oversaturated orange, or a glossy commercial finish.
- Audio: raw security-camera microphone sound. Quiet night ambience, faint leaves moving, subtle bear snuffling, candy-wrapper rustle, small plastic-bucket sounds, claws or paws contacting the porch, one abrupt startled animal vocalization if physically plausible, quick scrambling footsteps, and the faint sound of the homeowner reacting behind the glass. No soundtrack, no narrator, no captions, no voice-over, no added cinematic bass hit, and no artificial sting.
- The timestamp or security-camera interface may be minimally visible, but it must not distract. Do not generate legible brand logos, fake app notifications, random text, watermarks, or prominent UI overlays.
LOCATION AND BLOCKING
The location is an ordinary American suburban front porch decorated for Halloween. The door and its frame occupy the right side of the vertical image. The left and centre contain the porch floor, a small candy bucket, a seated life-size Halloween doll, and the top of two or three steps leading down into a dark front yard. The house siding and porch railing should remain fixed and geometrically consistent throughout the clip. Through the glass panel or glass in the front door, the homeowner can be seen inside the house, partially obscured by reflections and indoor darkness.
The porch should look lived-in and ordinary, not like a haunted attraction. Include a few restrained Halloween details: a small orange candy bucket with a simple pumpkin face, one or two small pumpkins, a short string of dim warm lights if naturally placed, and a life-size doll in a pale vintage dress. Do not clutter the scene. The candy bucket is placed on the porch floor near the doll, close enough for the bear to investigate without crossing the whole porch. A smartphone belonging to the homeowner rests near the threshold, on a narrow ledge or on the floor just inside the door's exterior edge, visible enough that the doll can plausibly reach it after the bear leaves. Keep the phone's position fixed until the final beat.
The doll is unsettling but physically plausible as a Halloween prop: a life-size child-sized figure with a worn pale face, old-fashioned light dress, dark hair, glassy eyes, and a slightly open neutral mouth. It should look like a real animatronic or antique-style Halloween decoration, not a supernatural creature. The hands are articulated prop hands, capable of a quick mechanical movement. The doll sits on a low porch chair or sturdy stool beside the candy bucket. Its feet, skirt, chair and hands must stay spatially consistent. At first, the doll is completely still. No blinking, no head turns, no torso motion, no moving hair, and no hint of movement before the eyes begin tracking the bear.
The bear is a realistic adult black bear of believable size and anatomy. Its fur is dark and textured, with natural highlights from the porch bulb. It moves cautiously, sniffing and investigating food, with appropriate weight transfer and four-legged gait. Its paws must contact the porch surface naturally. The bear must not behave like a human, grin, stand theatrically, or perform exaggerated cartoon movements. The startled response should be abrupt but physically credible: it jerks back, loses its balance for a fraction of a second, knocks the lightweight bucket over, then scrambles down the steps and disappears into the dark yard. Do not show injury, blood, or prolonged aggression. The doll's grab is a brief surprise action, not a sustained attack.
The homeowner is an adult visible behind the glass front door. They wear ordinary casual indoor clothing and remain inside. Their face should be only partly visible through reflections, but their reaction is readable: they witness the sudden grab, recoil, and instinctively cover their mouth. Do not make them open the door, step outside, speak directly to camera, or block the central action. Their movement should be small and believable, not a staged theatrical scream.
CONTINUITY RULES
The entire clip is one uninterrupted recording from the same fixed camera. No cuts, no angle changes, no zooms, no slow motion, no handheld movement, no re-framing, no time jumps, no transitions, and no flash frames. All characters and props occupy the same positions from start to finish unless moved by a visible physical action. The porch architecture, door frame, chair, steps, bucket, pumpkins, phone, and lighting must not change between frames. The bear's size and coat must remain consistent. The doll's face, dress, hair, hands, and body proportions must remain identical throughout. The homeowner remains behind the same glass door. The smartphone cannot teleport, duplicate, vanish, or change colour. The tipped candy bucket remains tipped after it is knocked over. Any spilled candy stays where it lands.
The camera must not pan toward the bear, follow it down the steps, or automatically zoom. The bear can leave the frame naturally through the lower-left or lower-centre steps. The final beat must still be readable in the same fixed composition: the bear has gone, the doll remains in its chair, and the doll is now holding the phone. Avoid any shot where the phone appears in the doll's hands before the bear has left. The phone must be physically reachable from the doll's seated position. If needed, place it on the low outer threshold or a narrow ledge beside the chair, within arm's reach, rather than several metres away. The doll should not cross the porch or move its chair to get it.
TIMED ACTION: FOLLOW THIS ORDER PRECISELY
0.0-2.5 SECONDS: ORDINARY, QUIET SETUP
Begin already recording, as if the motion alert has just started. The porch is quiet. The bear enters from the dark lower-left edge of the frame or is already just stepping onto the porch at the left edge. It approaches the candy bucket with a natural cautious gait, head lowered and nose working. The doll sits completely motionless beside the bucket. The homeowner is faintly visible behind the glass, standing inside and looking toward the porch. Nothing supernatural happens yet. The first seconds should be mundane and credible, so the later event feels surprising. Do not begin with a jump scare, a sudden close-up, a dramatic growl, or an obvious sign that the doll is alive.
2.5-6.5 SECONDS: THE BEAR INVESTIGATES THE CANDY
The bear reaches the bucket, sniffs it, nudges it gently with its nose, and picks up or mouths one piece of wrapped candy. It may use a paw to steady the bucket, but keep the movement animal-like and simple. The bucket gives a small plastic rattle. The bear's shoulders and back move with natural breathing. The doll remains perfectly still, facing forward. Its eyes do not yet move. The homeowner watches from inside but is not yet alarmed. Maintain the same camera exposure and composition; the warm porch light falls naturally across the bear's muzzle and the doll's pale face.
6.5-8.5 SECONDS: THE EYES TRACK
While the bear's nose is down near the candy bucket, the doll's pupils slowly shift sideways toward the bear. Only the eyes move. The head remains fixed, the chin remains at the same angle, the shoulders and dress remain still, and the hands remain resting in the same position. The eye movement should be subtle but unmistakable when noticed. It should look like a small concealed animatronic mechanism, not glowing supernatural eyes. No glowing pupils, no head rotation, no twitching limbs, no floating, and no exaggerated facial morphing. The movement lasts about one second, then the eyes hold their new direction. The bear does not instantly react; it continues sniffing for a brief moment, which makes the eye movement more unnerving.
8.5-10.5 SECONDS: THE BEAR NOTICES
The bear pauses mid-sniff. Its ears lift slightly, its head rises a little, and it looks toward the doll's face. It shifts its weight back by a small amount, then cautiously leans its muzzle closer as if trying to identify the object. The movement should be slow and curious, not aggressive. The doll's head and body remain absolutely fixed. Only its eyes continue to watch the bear. The room behind the glass stays quiet; the homeowner begins to lean forward slightly, trying to see what the bear is doing. The tension comes from the distance closing between a large real animal and a completely still prop.
10.5-12.0 SECONDS: A SHORT, TENSE PAUSE
The bear brings its muzzle close to the doll's face, stopping just short of touching it. Hold the stillness for a fraction of a second. The bear's nose twitches; its breath and soft snuffling are audible. The doll's eyes remain locked on the bear. The audience should have time to expect nothing more than a strange animatronic trick. Do not prolong the pause beyond what feels natural. The sudden movement must arrive before the tension becomes slow or repetitive. The bear's face, the doll's hands, and the bucket should all remain visible in the wide frame.
12.0-13.0 SECONDS: THE GRAB
In one fast, mechanically sharp action, the doll suddenly lifts both articulated hands and briefly grabs the bear's muzzle from the sides. The movement is startling and quick, like a concealed animatronic trigger firing. Both hands make visible contact with the fur around the muzzle, but do not cover the bear's eyes completely and do not deform the bear's skull. The doll's torso stays seated and anchored to the chair; its hips and legs do not slide, and the chair does not travel across the porch. The hands move from their resting position to the bear's muzzle in a single clear action. Do not create extra arms, elongated fingers, rubbery limbs, or impossible joint angles. The doll does not bite, growl, stretch its mouth unnaturally, or transform into a monster. The shock comes from a recognisable doll suddenly moving and grabbing the animal.
13.0-15.0 SECONDS: THE BEAR'S STARTLED ESCAPE
The bear reacts instantly and believably: a sharp backward jerk, a startled huff or yelp, a rapid pivot, and a scramble away from the doll. It bumps the candy bucket, which tips onto its side and spills several wrapped sweets across the porch floor. The bear's paws skid slightly but retain contact with the ground; its body mass and momentum feel real. It hurries down the steps and exits into the dark yard. The action is chaotic for a moment but never becomes an unreadable blur. The doll releases the bear as it pulls away and returns its hands toward its lap. The doll must not cling to the bear, fly off the chair, or pursue it. Do not show the bear attacking the doll or the homeowner. The escape should feel like a startled wild animal fleeing an unexpected mechanical movement.
15.0-17.5 SECONDS: THE HOMEOWNER REACTS
As the bear disappears down the steps, the homeowner behind the glass recoils from the door. They lift one hand to cover their mouth and take one or two involuntary steps backward. Their expression is startled disbelief, not a theatrical horror scream. Their reflection and the porch light may overlap naturally on the glass. They do not open the door or come outside. The audio captures a small muffled gasp or sharp intake of breath from inside, barely audible through the glass. The porch is now still except for a few sweets settling on the floor and the faint night ambience. The doll sits in its original position, once again completely motionless.
Alpha Mom retweeted
88 mph — straight back to childhood. Back to when we first believed anything was possible. ⚡️
Created with Seedance 2.5 and
@makeugc
#BackToTheFuture #DeLorean
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
He tried to fix her form. His body had other plans.
Made with Unlimited Seedance on @makeugc
Sound on. Watch the guy in the back right after he pulls. Could you have kept a straight face?
Prompt👇
Create a native 15-second, vertical 9:16 real smartphone video: one continuous take with no cuts, recorded by a phone propped on the floor in the free-weights area of an ordinary gym. It must look like a real clip a girl filmed of her deadlift set that accidentally caught a guy giving her unsolicited advice, failing to lift her bar and letting out an accidental quiet fart from the strain. No reference image.
CORE RULES
Two adults in focus: MAYA, a woman of 25, and JAKE, a man of 29. One continuous shot from the first frame to the last. The camera is fixed: the framing, the angle and the size of the people in the frame stay exactly the same from the first frame to the last; no push-in, no zoom, no pan, the camera never follows the action. Each person keeps the same face, hair, body and outfit throughout. Each has exactly two arms and two legs; each hand has five fingers; joints bend only naturally. The recording phone is never visible. Natural, understated behaviour: nobody performs for the camera. Fluid real-time motion, no freezes, no slow motion. No readable text, numbers, logos, swooshes, stripes or brand marks anywhere, including all clothing and shoes.
CHARACTER
Tone: a real, awkward gym moment caught by accident. Funny because it is real and quiet.
MAYA is a beautiful, eye-catching 25-year-old woman, naturally sexy in an effortless, believable way. She has an athletic, curvy, strong figure with a full, large, natural-looking bust, a defined waist and realistic body proportions. Long dark-brown hair in a high ponytail with a few loose flyaways, never across her face. She wears a fitted black sports bra with a softly scooped neckline under an open cropped teal-grey zip hoodie, fitted high-waisted black leggings and flat black training shoes. Small gold hoop earrings. Fresh, glowing everyday makeup: defined brows, soft mascara, nude lip gloss; slightly shiny skin from effort, a little flushed after her set. She looks confident and attractive, but the clip stays about the lift and her face, never about her body. No logos.
JAKE is a 29-year-old gym guy who acts like an expert: short light-brown hair, neat short beard, average fit build. He wears a plain grey t-shirt, completely plain black joggers with no logo, plain white sneakers with no logo and a plain black lifting belt around his waist.
FACE
MAYA: oval face with high cheekbones, almond-shaped warm brown eyes with long dark lashes, defined natural brows, full lips with nude gloss, small mole above the LEFT corner of her upper lip, straight natural white teeth, warm olive skin with a healthy glow. Focused while lifting; then patient and amused; then trying hard not to laugh; then laughing.
JAKE: rounded face, blue-grey eyes, neat beard. Confident and teacher-like, then strained and red, then frozen with wide eyes after the sound, then pretending nothing happened.
Both: eyes focus on what they look at, gaze moves before the head, natural blinking, gradual expressions, head turns under 30 degrees. Nothing ever covers either face. No cartoonish faces, no shouting, no glassy eyes, no warped teeth.
VOICE
JAKE: confident, slightly patronising, medium volume, American accent, two short lines. MAYA: one line at the end, said through soft laughter, low and dry, soft American accent. Both recorded by the phone microphone on the floor: slightly muffled, roomy, with gym noise under it. Every word matches the speaker's lips. Each line is said once.
CAMERA
A phone propped upright on the floor against a water bottle, about 2.5 metres away, placed at a 45-degree angle in front of and to the LEFT of the barbell, lens about 30 cm above the floor, angled slightly up, wide front-camera field of view. The barbell runs diagonally across the lower part of the frame, fully visible with all its plates. Both people are seen at a three-quarter angle from head to feet the whole time. When MAYA bends over the bar, the camera sees her from the side-front: her face, arms, back and the bar, never looking straight down her top. Locked and static for the whole clip. Horizon tilted about 2 degrees. The phone is never visible. This exact framing never changes.
CAMERA HAND
Nobody holds the camera. It stays propped on the floor the entire time.
HANDHELD
No handheld movement. The camera stays completely still. Never gimbal-smooth, never shaking.
LOOK
Real smartphone footage: slight wide-angle distortion near the edges, mild noise in darker areas, light compression, auto-exposure that slightly overexposes the windows, auto white balance leaning a little cool under fluorescent light. Ordinary colours, flat contrast, no colour grading, no film look, no warm tint, no shallow depth of field. Natural skin with pores, sweat shine and redness. No beauty filter, no plastic skin, no glossy commercial finish.
LIGHTING
Available light from the ceiling fixtures and practical lamps present in the scene. Slightly uneven illumination, believable shadows and modest colour-temperature differences between existing light sources. Preserve realistic skin tones and readable surroundings. No added studio lighting, dramatic spotlighting or artificial glow.
VISUAL MATCH
The image must look exactly like an ordinary phone clip from a busy budget chain gym on a weekday evening: flat white fluorescent ceiling panels, a worn and scuffed black rubber floor with a square lifting platform, chalk marks on the platform, a plate rack with mismatched plates, a dumbbell left on the floor near the rack, a towel hanging on the squat rack, a mostly blown-out window wall, a wall fan. Low phone-on-the-floor angle. Everything is in focus. Slightly messy, lived-in, ordinary. Nothing looks styled, lit or composed like a studio.
SETTING
The free-weights area of a regular budget chain gym in the evening. One standard steel barbell on a plain black rubber lifting platform, loaded with two identical large blue rubber plates on each side, held by plain black collars. The plates have no numbers or text. Behind the platform: a plate rack, a squat rack with a towel on it, a dumbbell rack, a wall fan and an overexposed window wall. Far in the back, about 10 metres away, one ordinary gym-goer does bicep curls. No mirrors.
BACKGROUND
Readable instantly as a gym free-weights area. Three layers: the edge of the platform and the floor in the near foreground; MAYA, JAKE and the loaded barbell in the middle; the racks, the window wall and the distant gym-goer behind. Palette: black rubber, grey metal, white light, the blue plates as the only strong colour accent, the teal-grey hoodie and grey t-shirt. Background story: at 10.4 s, right after the sound, the distant gym-goer freezes mid-curl and slowly turns his head toward JAKE; at 13.0 s he looks away and goes back to curling, pressing his lips together, without coming closer. The background never warps.
MOTION
Real movement with weight. MAYA's deadlift reps are strong and controlled: hips and knees straighten together, back stays flat, bar travels straight up close to her legs, then is lowered under control and lightly touches the floor. JAKE moves with expert confidence, then real strain, then a stiff, awkward stillness. Eyes lead, then head, then shoulders. Left and right sides never mirror. No freezes, no slow or sped-up motion, no posing.
DEFECT PREVENTION
Hands: MAYA grips the bar with both hands overhand, shoulder-width apart, from the first frame until she sets the bar down at 4.3 s; then both hands give one small shake at her sides; from 7.0 s to 10.8 s her arms are crossed over her chest, both hands visible on her upper arms; when she laughs her hands stay crossed, then drop to her sides, never touching her face. JAKE points only with his RIGHT index finger at 5.0 s, other fingers curled. When he lifts, both his hands grip the bar overhand, shoulder-width apart; at 11.2 s both hands open slowly and leave the bar together. Five fingers per hand; fingers never merge with the bar, each other or the body.
Face: both faces stay visible the whole time; nothing covers either face. MAYA's laugh starts with pressed lips and shaking shoulders, then a short laugh with only upper teeth visible. JAKE's strain shows as a red face, tight lips and a tense neck, not a cartoon grimace; after the sound his eyes widen slightly and he stares straight ahead. Head turns under 30 degrees.
Body and legs: MAYA does exactly two visible reps: the first frame shows her already standing at lockout of rep two; she lowers it and lifts rep three, then lowers and sets the bar down at 4.3 s, and stands up. Each rep the bar touches the floor lightly once. JAKE's pull: he bends his knees and hips, back fairly straight, pulls up, and the barbell does not leave the floor at all; his feet stay planted. MAYA stands to the LEFT of the bar from 4.5 s; JAKE stays behind the bar until 11.2 s, then straightens up in place. Exactly two arms and two legs each; legs keep a constant length; feet never slide.
Objects: one barbell, four blue plates (two per side), two black collars, one water bottle with the phone off-screen. The barbell stays straight and rigid, never bends, never floats, never bounces; it only moves while MAYA lifts it. Objects never vanish, duplicate, change shape or colour, or pass through bodies. No readable text, numbers or logos.
Continuity: one continuous take, no cuts, identical framing and camera distance from first to last frame, same outfits, same light. MAYA is on the LEFT side of the frame after her set; JAKE enters from the RIGHT and stays at the bar.
Physics and environment: the bar only moves during MAYA's reps, straight up and down. No mirrors, windows show no reflections. Only the one distant gym-goer appears; nobody else comes near.
STORYBOARD (15 s, one continuous take)
START POSE: The first frame shows MAYA mid-set, standing tall at lockout with the loaded bar at her thighs, both hands gripping it, shoulders back, face focused, a breath held, ponytail still. The platform, the blue plates and the gym behind are clearly visible. JAKE is not yet in frame.
00:00.0-00:01.6 - MAYA lowers the bar under control: hips back, knees bend, back flat; the plates touch the floor lightly with a soft thud. FACE: lips pressed, eyes on the floor ahead.
00:01.6-00:03.0 - She lifts rep three in one strong motion to lockout, a short exhale through her lips. FACE: focused, a small effort frown.
00:03.0-00:04.3 - She lowers the bar again under control and sets it down on the platform; the plates thud softly and settle.
00:04.3-00:05.0 - She stands up, steps half a step to the LEFT of the bar, shakes both hands once at her sides, a satisfied breath. JAKE walks into frame from the RIGHT and stops at the RIGHT end of the bar.
00:05.0-00:06.2 - JAKE (confident, teacher-like; not rude): "Hey, your form is OFF." He points at her back with his RIGHT index finger. FACE MAYA: eyes move to him, brows lift slightly.
00:06.2-00:07.4 - JAKE (patronising, friendly; not loud): "Let me SHOW you." MAYA steps one more step to the LEFT and crosses her arms. FACE MAYA: a tiny amused closed-lip smile.
00:07.4-00:09.0 - JAKE steps behind the bar, plants his feet, rolls his shoulders, bends his knees and hips and grips the bar with both hands. FACE JAKE: confident, a small smirk toward MAYA.
00:09.0-00:10.2 - He pulls hard. His arms straighten, his back tightens, his face reddens, a low grunt; the bar does not move at all.
00:10.2-00:10.6 - At the peak of the strain, a short, soft, muffled fart sound comes from JAKE: one brief low "pfft", about 0.4 seconds, clearly audible on the phone microphone but not loud, natural and real, not cartoonish. His body freezes in the pull position.
00:10.6-00:11.2 - Silence for a beat. FACE JAKE: eyes widen slightly, stare straight ahead, lips pressed. FACE MAYA: her eyes go wide, her lips press tightly together, her shoulders start to shake.
00:11.2-00:12.4 - JAKE slowly lets go of the bar with both hands and straightens up in place, staring at the bar as if nothing happened, adjusts his belt with both hands. MAYA turns her head about 25 degrees away to the LEFT, a short muffled laugh escapes through her nose, her arms still crossed.
00:12.4-00:13.0 - MAYA turns back, eyes come to the lens, still laughing softly, upper teeth visible; her arms uncross and drop to her sides.
00:13.0-00:14.4 - MAYA (through soft laughter, dry; not mocking, not loud): "Form looks fine to ME."
00:14.4-00:15.0 - She bites back another laugh, a wide smile with upper teeth; JAKE behind the bar looks up at the ceiling and exhales slowly through puffed cheeks.
SOUND
Real phone-on-the-floor audio: gym hum, distant clank of weights, faint gym music with no lyrics far away, the soft thuds of the plates on each rep, MAYA's controlled exhales, footsteps on rubber, JAKE's two lines, his sharp breath and low grunt, then one short, soft, muffled natural fart sound at 10.2 s, about 0.4 seconds, audible but not loud, followed by a beat of near silence with only the gym hum, then MAYA's muffled laugh through her nose, her line through soft laughter, and JAKE's slow exhale.
HANDS AND FEET
Five fingers on each hand, never merging with each other, the bar or the body. Nobody touches their face. Exactly two arms and two legs each; knees follow the toes; feet stay planted during every lift and never slide.
CONTINUITY AND REALISM
One continuous take. Two main people, one distant gym-goer, one barbell with four blue plates and two collars, all in the same places from start to end. No floating or disappearing objects, no transformations, no captions, logos or watermarks. The framing never emphasises her chest or body; when she bends to lift, the camera sees her from the side-front and the focus stays on the bar, her face and the motion. Everyone is an adult.
FINAL FEEL
A real, unedited phone clip from an ordinary gym: a girl finishes her heavy set, a guy comes to correct her form, can't move her bar and lets out an accidental quiet fart, and she can't hold her laugh. Real, imperfect, phone-recorded. Not a commercial. Not a fashion shoot. Not polished influencer content.
Alpha Mom retweeted
essa tal de IA tá d+ ein
Made with Seedance 2.5 on @makeugc (native 15-second video, no editing)
PROMPT ⬇️
**CAMERA:**
DV 16mm tape camcorder handheld feel. MILA films the opening and closing selfies herself; her gym friend films the dumbbell exercises handheld. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder and camera operator never appear 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 effort mixed with humor. Quick, casual cuts between excerpts from an ongoing workout. Exercise shots begin and end mid-set, with continuous rhythmic repetitions at normal speed. She talks while moving, without stopping to pose. Time passes between clips; equipment setup and camera handoffs happen off-screen.
**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.
**Setting**
A gym dumbbell area in the evening — weight racks, benches, soft overhead lighting. Two other gym-goers exercise casually in the background, away from MILA. An angled mirror naturally reflects her back, blue shorts and legs in wider shots. She uses the same matching pair of small black hex dumbbells throughout.
**Storyboard (15s, 6 shots)**
1. *(0–2.5s, moving arm’s-length selfie)* Already walking past the weight rack, MILA smiles toward the lens and briefly glances at the equipment. Her face and blue sports bra are visible; the framing bobs with her footsteps. MILA: “Arm day. This should be quick.”
2. *(2.5–5s, handheld medium shot)* Cut into an ongoing set of standing alternating dumbbell curls. One arm rises as the other lowers; she keeps the rhythm while speaking. The camera drifts slightly with the operator’s movement. MILA: “These felt lighter yesterday.”
3. *(5–7.5s, handheld wider three-quarter shot)* Another excerpt: MILA is already doing lateral raises, repeatedly lifting and lowering both dumbbells without holding a pose. Her rear view is visible in the mirror. MILA (breathless): “I picked the light ones!”
4. *(7.5–9.5s, handheld close-up insert)* Her hand and forearm grip a dumbbell through the continuing repetitions. The camera briefly loses focus as the weight moves, then catches it again. No dialogue — breathing and distant gym sounds.
5. *(9.5–12s, handheld medium-wide shot)* MILA walks briskly past the camera toward the rack, carrying both dumbbells beside her thighs. The operator turns to follow her as she laughs. MILA: “Yep — my arms just quit.”
6. *(12–15s, arm’s-length selfie after the set)* A clear jump cut: the dumbbells have been returned, and MILA is already holding the camera herself. Walking out of the weights area, she shakes out her free hand and grins. MILA: “Same time tomorrow? No promises.”
#AIVideo
Alpha Mom retweeted
She had 30 seconds to outrun death. ⚡
Unlimited Seedance 2.5 on @makeugc
prompt
🎬 MAIN CHARACTER — CHARACTER CONSISTENCY
Heroine: {{Image 1}}
A beautiful 19-year-old Korean university student with long black hair tied in a messy high ponytail. She wears a black fitted school-style blazer, white shirt, loosely tied black necktie, short dark-gray pleated skirt, black knee-high socks, and black leather shoes.
Her face is sweaty, with a small scratch on her cheek. Her hair flies wildly during movement.
Personality: Fearless but visibly terrified. Extremely athletic, with exceptional parkour abilities and lightning-fast reflexes.
Important: Her facial features, hairstyle, clothing, and body proportions must remain perfectly consistent throughout the entire sequence.
🎥 DETAILED 30-SECOND VIDEO PROMPT
⏱️ SCENE 1 — THE HORDE IS COMING (0–4 SECONDS)
Camera: Extreme wide-angle shot transitioning into a fast backward tracking shot.
A breathtaking transparent glass skybridge connects two enormous luxury shopping towers, suspended 40 floors above the crowded streets of Seoul.
The bridge is approximately 60 meters long, with transparent glass flooring, glass side panels, and sleek steel support beams.
Suddenly, the heroine bursts through the entrance doors, sprinting at maximum speed.
Behind her, more than 100 terrifying infected zombies explode through the mall entrance.
Their bodies slam into the glass walls.
Some run on all fours.
Others violently shove past one another.
The girl looks backward while running.
Her eyes widen in absolute terror.
Suddenly, the glass beneath her left foot cracks.
A spiderweb of fractures spreads across the transparent floor.
She gasps but keeps running.
Sound: Deafening zombie screams, pounding footsteps, rapid heartbeat, cracking glass.
Camera effect: Aggressive handheld movement with realistic motion blur.
⏱️ SCENE 2 — THE BRIDGE STARTS BREAKING (4–9 SECONDS)
Camera: Low-angle tracking shot focusing on her feet, followed by a terrifying overhead view.
The heroine sprints across the transparent bridge.
Forty floors beneath her, tiny cars move along the streets.
Suddenly—
CRAAAAACK!
An enormous glass floor panel shatters directly behind her.
Three pursuing zombies plunge through the opening.
The girl screams and accelerates.
Another glass panel explodes beneath her next step.
She launches herself forward.
Her body flies across a widening gap.
She lands hard on the next intact panel.
The impact creates another spiderweb of cracks.
She immediately rolls forward and scrambles to her feet.
Behind her, zombies continue charging.
Their combined weight causes multiple floor panels to collapse in rapid succession.
Visual: Shattered glass rains down between the skyscrapers.
Sound: Explosive glass fractures, rushing wind, screaming infected creatures.
Action requirement: Every jump must have believable weight, gravity, momentum, and physical impact.
⏱️ SCENE 3 — THE ZOMBIE GRABS HER (9–14 SECONDS)
Camera: Tight handheld close-up transitioning into a dramatic side-tracking shot.
The girl races toward the middle of the bridge.
Suddenly, an infected zombie lunges from behind and grabs her blazer.
She is violently pulled backward.
Her feet slide across the cracked glass.
The zombie opens its mouth inches from her face.
She screams.
In one explosive movement, she drives her elbow backward into its face.
The infected creature staggers.
She spins and delivers a powerful flying kick to its chest.
The zombie crashes against the glass railing.
BOOOOM!
The railing shatters.
The zombie tumbles backward into open space.
But the force of the impact causes the entire bridge to shake.
A steel support connection snaps.
The bridge tilts dangerously sideways.
The heroine loses her balance.
She drops onto her stomach and desperately grabs a steel floor support.
Sound: Brutal impact, breaking glass, twisting metal, desperate screaming.
⏱️ SCENE 4 — THE IMPOSSIBLE PARKOUR ESCAPE (14–20 SECONDS)
Camera: Dramatic overhead shot followed by a fast side-view tracking movement.
The entire bridge begins collapsing section by section.
The heroine pulls herself upright.
Ahead of her, the remaining glass floor explodes into fragments.
A massive six-meter gap opens directly in front of her.
Behind her, dozens of zombies are approaching.
There is nowhere to run.
She looks toward the opposite side.
Her breathing becomes frantic.
Then she spots a narrow steel maintenance beam running alongside the shattered bridge.
She jumps onto the beam.
Her shoes barely find balance.
She sprints along the narrow metal structure.
The camera follows from above, revealing the terrifying 40-story drop.
Suddenly, a zombie leaps toward her from the remaining bridge.
She ducks.
The infected creature flies over her and disappears into the open air.
The steel beam bends under her weight.
She reaches its end.
The beam suddenly breaks loose.
She leaps forward at the last possible moment.
Sound: Thunderous metal snapping, powerful wind rush, rising orchestral tension.
⏱️ SCENE 5 — THE MOST TERRIFYING MOMENT (20–25 SECONDS)
Camera: Wide cinematic side shot transitioning into extreme slow motion.
The heroine launches herself through the air toward the opposite shopping tower.
Behind her, the remaining glass skybridge collapses.
Hundreds of glass fragments explode outward.
Steel support beams twist and fall.
Zombies tumble with the collapsing structure.
The camera captures the heroine suspended in midair.
Her hair flies backward.
Her arms stretch desperately toward the opposite building.
Her expression is pure terror.
She misses the landing.
Her body drops below the edge of the opposite platform.
At the very last second—
HER RIGHT HAND CATCHES A STEEL MAINTENANCE RUNG.
Her entire body jerks downward.
Her shoulder strains under the impact.
Her legs swing violently above the enormous drop.
She screams.
Sound: Sudden orchestral silence followed by a massive metallic impact and desperate gasp.
⏱️ SCENE 6 — THE FINAL NIGHTMARE (25–30 SECONDS)
Camera: Extreme close-up of her trembling hand, followed by a dramatic overhead crane shot.
The girl hangs 40 floors above Seoul.
Her fingers slowly slip from the steel rung.
She looks upward.
Her face is covered in sweat.
She desperately reaches with her free hand and grabs the rung.
Using her remaining strength, she begins pulling herself upward.
Her body trembles.
She finally reaches the platform.
She rolls onto the floor, gasping for air.
For one brief second, everything becomes silent.
She raises her head.
Suddenly, hundreds of zombies appear behind the glass entrance doors directly in front of her.
Their faces press against the glass.
Their hands pound against the doors.
The heroine freezes.
Her eyes widen.
A massive crack spreads across the entrance.
BOOOOOOM!
The doors explode outward.
The zombies charge directly toward her.
CUT TO BLACK.
FINAL TEXT:
"SHE ESCAPED THE FALL. NOT THE DEAD."
Sound: One deafening zombie scream followed by absolute silence.
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
This thing is really crazy!
I think AI generated content is the future of entertainment.
Made with Seedance 2.5 on @makeugc (native 15-second video, no editing)
PROMPT ⬇️
**CAMERA:**
DV 16mm tape camcorder handheld feel. MILA films the opening and closing selfies herself; her gym friend films the dumbbell exercises handheld. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder and camera operator never appear 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 effort mixed with humor. Quick, casual cuts between excerpts from an ongoing workout. Exercise shots begin and end mid-set, with continuous rhythmic repetitions at normal speed. She talks while moving, without stopping to pose. Time passes between clips; equipment setup and camera handoffs happen off-screen.
**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.
**Setting**
A gym dumbbell area in the evening — weight racks, benches, soft overhead lighting. Two other gym-goers exercise casually in the background, away from MILA. An angled mirror naturally reflects her back, blue shorts and legs in wider shots. She uses the same matching pair of small black hex dumbbells throughout.
**Storyboard (15s, 6 shots)**
1. *(0–2.5s, moving arm’s-length selfie)* Already walking past the weight rack, MILA smiles toward the lens and briefly glances at the equipment. Her face and blue sports bra are visible; the framing bobs with her footsteps. MILA: “Arm day. This should be quick.”
2. *(2.5–5s, handheld medium shot)* Cut into an ongoing set of standing alternating dumbbell curls. One arm rises as the other lowers; she keeps the rhythm while speaking. The camera drifts slightly with the operator’s movement. MILA: “These felt lighter yesterday.”
3. *(5–7.5s, handheld wider three-quarter shot)* Another excerpt: MILA is already doing lateral raises, repeatedly lifting and lowering both dumbbells without holding a pose. Her rear view is visible in the mirror. MILA (breathless): “I picked the light ones!”
4. *(7.5–9.5s, handheld close-up insert)* Her hand and forearm grip a dumbbell through the continuing repetitions. The camera briefly loses focus as the weight moves, then catches it again. No dialogue — breathing and distant gym sounds.
5. *(9.5–12s, handheld medium-wide shot)* MILA walks briskly past the camera toward the rack, carrying both dumbbells beside her thighs. The operator turns to follow her as she laughs. MILA: “Yep — my arms just quit.”
6. *(12–15s, arm’s-length selfie after the set)* A clear jump cut: the dumbbells have been returned, and MILA is already holding the camera herself. Walking out of the weights area, she shakes out her free hand and grins. MILA: “Same time tomorrow? No promises.”
#AIVideo
Alpha Mom retweeted
🩷ONE KISS. EVERYTHING CHANGES.
She didn’t wait for him to become an angel.
Seedance 2.5 on @makeugc
Cold light, a trembling camera, and a transformation that begins with a kiss. I wanted this AI-generated scene to feel like a half-remembered dream.
Would you call this love… or magic?
🤝 Paid partnership · 🤖 Made with AI
Alpha Mom retweeted
Let's have some fun! I made this experimental trailer using WAN 3.0's character replacement feature. Huge thanks to @makeugc for giving us access to all the top AI models!
What if we replaced one of the main characters in GTA VI with someone completely unexpected? Mr. Bean is pretty unexpected, right?
All you need to get a result like this is 3 simple steps:
1️⃣ Upload the original video.
2️⃣ Upload reference images of the character.
3️⃣ Describe in the prompt who you want to replace.
WAN 3.0 understands prompts really well and doesn't require any strict rules or complicated instructions. I've tested it myself!
Would you like to see the full version of the trailer?
#aivideo #GTA6
🤝 Paid partnership · 🤖 Made with AI
What could the main menu and loading screens in GTA VI look like?
Let's imagine it with the help of WAN 3.0 on @makeugc!
Here's my fan concept of the GTA VI main menu and loading screens. What do you think?
Curious how I made it? It's actually pretty simple!
First, generate some artwork using style references. Then bring those images to life with WAN 3.0. Just ask the model to "animate the image" — you can even specify exactly which elements should move and which should stay completely still.
Want to try it yourself? Check out my link in the comments and get access to some of the best AI models for just $1!
#AIVideo #GTAVI #GrandTheftAuto6 #GrandTheftAutoVI #funconcept
Alpha Mom retweeted
⚠️ Seedance 2.5 vs Kling 4.0 - same transformation test, and Kling got crushed
Made with Seedance 2.5 on @makeugc
I am shocked and very angry.
And now the question:
- Is it an overrated model?
- Maybe something is wrong with the prompt?
- Is it perhaps better suited for other tasks?
Kling 4.0:
❌ The model turned out to be more expensive in terms of generation credits, and the result did not satisfy me at all - the realism is worse
Seedance 2.5:
✅ Did it 100%
Parameters: 16:9 / 15 sec / 720p
Same prompt and same reference, but different results
🤝 Paid partnership · 🤖 Made with AI
⚠️People urgently need to come up with a raincoat for cycling.
Made with Seedance 2.5 on @makeugc
Prompt
Create a 15-second photorealistic video, 16:9, using the attached image as the opening frame and strict visual reference.
Preserve the elderly man's exact identity: swept-back silver hair, round glasses, gray mustache and goatee, charcoal suit, blue shirt, navy tie and black backpack. Preserve the silver bicycle and its large transparent rain capsule, including its rounded shape, metal supports and clear panels.
Preserve the white-and-brown Jack Russell terrier and its miniature transparent rain capsule. The dog's capsule encloses its head and torso, with FOUR separate openings for its legs. Each leg stays through its own opening throughout the video. The dog runs on its own paws; its capsule has no bicycle, wheels or motor.
SETTING:
A rainy Tokyo business district with modern glass office buildings, warmly illuminated interiors, green sidewalk railings, pedestrian crossings and commuters carrying umbrellas. Wet asphalt reflects windows and traffic lights. Steady natural rainfall, gray daylight, realistic subdued colors. The scene feels like an unusual invention casually filmed on a real city street.
0–5 SECONDS:
Begin with the exact composition of the reference image, immediately in motion. The elderly man pedals smoothly toward the left at a relaxed cycling pace. The dog runs alongside him on the camera-facing side, slightly ahead of the front wheel, maintaining a clear lateral gap.
The camera tracks parallel to them in a medium-wide side view. Keep the entire bicycle, roof of the capsule and all of the dog's paws inside the frame. Buildings and pedestrians move naturally across the background.
5–10 SECONDS:
Continue the uninterrupted tracking shot. The man keeps both hands on the handlebars and looks calmly ahead. His legs drive the pedals continuously; the crank, chain and wheels move consistently with his speed.
The terrier maintains an energetic, natural running gait matching the bicycle's pace. Its paws make clear contact with the road, producing small splashes. Its lightweight capsule gently bobs with its torso while retaining its exact shape. The four leg openings remain fixed in the shell, allowing free leg movement.
Raindrops collect and slide down both transparent capsules. Preserve realistic visibility and subtle refraction through the plastic.
10–15 SECONDS:
The camera gradually moves slightly ahead and turns toward the subjects, transitioning smoothly from side profile into a front three-quarter tracking view while continuing to move with them.
Reveal more of the elderly man's face through the curved clear windshield. Keep the dog fully visible beside him, separated from the bicycle wheels. Both continue forward at the same steady pace.
Finish with both subjects still moving naturally through the rainy street.
CAMERA AND STYLE:
One continuous take. Natural street-video realism, subtle handheld micro-movement, believable perspective and restrained motion blur. No dramatic zooms, slow motion, cuts or exaggerated cinematic effects. The absurd rain capsules are treated as ordinary everyday objects.
AUDIO:
Natural rain pattering against clear plastic, tires rolling over wet asphalt, light bicycle mechanism sounds, quick soft paw splashes and distant city traffic. No dialogue, narration or music.
CONSISTENCY:
Keep the man's face, age, clothing and backpack unchanged. Keep the dog's breed, markings and proportions unchanged. Maintain the exact construction of both capsules. No morphing, extra limbs, paws passing through solid plastic, sliding feet, floating wheels or distorted bicycle geometry. No collisions or pedestrians obstructing the main subjects. No captions, logos or watermarks.