yiha.ai

One prompt. 30s. 4K. 50 refs. Seedance 2.5 is live here: yiha.ai/seedance2.5 This is one-click filmmaking.

This is the remix link: yiha.ai/create?task=e1…

@ yiha.ai created with this prompt: 15 seconds, 16:9 cinematic, single continuous handheld tracking shot following the dancer, smooth flowing camera movement matching her motion, no hard cuts.\n\nGlobal setup: Artistic golden hour dance film. Warm low angle sunlight, soft lens flare drifting across frame, fine dust particles visible catching the light. Setting: an open field or rooftop at golden hour, tall grass swaying gently, wide open sky with warm amber tones. Subject: a young dancer in flowing lightweight clothing (loose dress or wide leg pants), expressive contemporary dance movement, fluid and graceful. Ambient sound: soft ambient instrumental music with a gentle building rhythm, wind through grass, fabric movement.\n\n[0:00–0:03] She stands still, arms relaxed, sunlight haloing around her silhouette, then begins a slow extending arm movement as the camera starts a gentle orbit.\n\n[0:03–0:06] She spins slowly, fabric flowing outward with the motion, hair catching the golden light, camera tracking smoothly alongside the turn.\n\n[0:06–0:09] She drops into a low fluid movement, reaching toward the ground then rising again in one continuous motion, dust and light particles visible around her.\n\n[0:09–0:12] She extends into a graceful leap or reach upward, silhouette framed against the golden sky, camera tilting up to follow the motion.\n\n[0:12–0:15] She settles into a final still pose, chest rising with breath, warm light flaring softly across the lens. Slow fade to white-gold light.\n\nStyle: warm painterly golden hour color grade, soft natural film grain, expressive fluid movement, artistic and atmospheric rather than technical. Constraints: consistent appearance and outfit throughout, physically plausible dance movement, no distorted anatomy or limbs, no text overlays, camera motion stays smooth and continuous throughout.

This is the remix link: yiha.ai/create?task=33…

@ yiha.ai created with this prompt: 15-second ultra-realistic comedy short, photorealistic live-action style, harsh fluorescent store lighting with neon spill, high detail fur and whiskers, realistic physics, smooth motion, cinematic camera work, funny animal voices with expressive faces. Setting: a small 24-hour convenience store at night, fluorescent overhead lighting mixed with neon window signs glowing outside, cramped snack aisles, a humming drink fridge, a counter with a lottery display, light rain visible through the glass storefront. Dialogue (spoken naturally with funny voices): Ziggy (smooth con-man voice): \"Evening, officer. Lovely fluorescents tonight.\" Sarge (gravelly, suspicious): \"Paws where I can see 'em.\" Ziggy (offended): \"This? I'm just holding it.\" Sarge (barking into radio): \"10-31! DONUT DOWN!\" Deb (flat monotone): \"Not my problem.\" Shot-by-shot timing: [0-3s] Low tracking shot down a snack aisle: a plump grey raccoon with a black bandit mask marking, wearing a tiny open Hawaiian shirt, with remarkably dexterous little black hands, strolls casually while one hand — behind his back — juggles a glazed donut. He nods at the camera: \"Evening, officer. Lovely fluorescents tonight.\" [3-6s] Whip-pan to a stocky fawn-colored pug with a black wrinkled face, wearing a tiny navy-blue security vest with a gold \"SECURITY\" badge and a small utility belt with a mini flashlight, standing at the end of the aisle, flashlight beam hitting Ziggy's face like an interrogation lamp. Sarge growls: \"Paws where I can see 'em.\" [6-9s] Close-up: Ziggy slowly raises both empty hands — while his tail, curled behind him, is visibly holding the donut. He says, deeply offended: \"This? I'm just holding it.\" [9-12s] The donut slips off the tail, rolls down the aisle in a perfect line like a wheel, realistic wobble physics. Both animals watch it, frozen. Then Sarge scrambles after it, tiny legs sliding on polished floor, barking into a shoulder radio: \"10-31! DONUT DOWN!\" [12-14s] Quick cutaway: a scruffy grey Virginia opossum wearing a red employee vest with a crooked name tag reading \"DEB\" watches the donut roll past the counter, deadpan, and says: \"Not my problem.\" The donut rolls out the automatic door into the rain. [14-15s] Freeze-frame hero shot: Sarge and Ziggy side by side at the open door, both staring into the rain at the lost donut, equally devastated. Text overlay optional: \"Nobody won tonight.\" Global style: Extremely realistic fur, whisker, and skin details, harsh fluorescent store lighting with soft neon spill from window signs, realistic reflections on the polished floor and fridge glass, subtle dust particles in light beams, flawless physics for all objects, highly expressive animal faces, comedic timing, 4K photoreal quality, no deformities.

Which building do you like the most?

This is the remix link: yiha.ai/create?remix=3…

@ yiha.ai created with this prompt: [STYLE] Celebration showcase film, photorealistic live-action cinematography, epic aerial visuals, 8K ultra HD, DaVinci professional color grading, high-contrast night lighting\n[DURATION] 15 seconds\n[SETTING] Statue of Liberty in New York Harbor at night → Las Vegas Sphere → city night sky drone light show, three locations connected by montage\n\n[00:00-00:05] Shot 1: Fireworks Opening (Aerial Orbit + Fireworks)\nAerial orbit: the camera dives down from the night sky and circles halfway around the Statue of Liberty. The verdigris copper statue is lit by golden floodlights from below, the torch glowing bright at the top.\nVFX: massive realistic pyrotechnics burst in continuous succession in the night sky behind the statue — red, white, and blue sparks bloom in spherical bursts, ember trails drift slowly downward, smoke dispersed by the night wind.\nSound: whistling of fireworks launching + triple low-frequency explosion rumble.\n\n[00:05-00:10] Shot 2: The Sphere Lights Up (Sphere Light Show + Match Cut)\nHard match cut: the firework sparks instantly transform into LED light dots on the surface of the Las Vegas Sphere.\nMedium-wide low-angle shot: waves of red, white, and blue light roll across the giant sphere's surface, converging into a massive golden number \"250\" with flowing particle texture on its surface; the sphere bathes the surrounding streets in warm golden light.\nSlow push-in: the number \"250\" gradually fills the frame.\nSound: low-frequency electronic swell building up, distant crowd cheering (off-screen).\n\n[00:10-00:15] Shot 3: Drone Swarm Finale\nWide low-angle shot: thousands of drone lights converge from all directions in the city night sky, first forming a star pattern, then flowing and morphing into glowing text \"1776 → 2026\".\nVFX: a final row of fireworks launches simultaneously from the horizon and bursts, golden ember rain filling the lower edge of the frame as the drone text freezes amid the firelight.\n[ON-SCREEN TEXT] Golden serif title fades in at center frame: \"250 YEARS\", softly glowing, holds for 1 second to close.\nSound: orchestral score peaks then cuts abruptly, leaving only the echo of fireworks.

Which building do you like the most?#transformers #miniatures #landmark

This is the remix link: yiha.ai/create?remix=2…

@ yiha.ai created with this prompt: Use the uploaded storyboard image as a visual reference only. Create a single 10-second cinematic 3D animation by recreating every storyboard panel in sequence. Do NOT animate the storyboard page itself. Rebuild every scene as a real animated environment while keeping the exact same girl, outfit, hairstyle, facial features, kitchen, colors, lighting, props, and overall style from the storyboard. 0.00–1.25s: The girl happily waves at the camera and points toward the cupcake ingredients on the table. 1.25–2.50s: She pours flour into a clear glass bowl. Soft flour particles float naturally. 2.50–3.75s: She gently whisks the cupcake batter while smiling. 3.75–5.00s: Extreme close-up of creamy batter being poured into colorful cupcake liners. 5.00–6.25s: She sprinkles rainbow sprinkles over the cupcake batter. 6.25–7.50s: Top-down shot of the cupcake tray as she carefully places it into the oven. 7.50–8.75s: Inside the oven, the cupcakes rise into fluffy golden cupcakes with warm glowing light. 8.75–10.00s: She removes the cupcakes, proudly presents them to the camera, smiles brightly, and gives a cute thumbs-up. Style: Pixar-quality 3D animation, ultra-cute, cozy bakery kitchen, warm golden lighting, soft pastel colors, cinematic depth of field, smooth camera movements, realistic hand movements, natural facial expressions, seamless transitions, high detail, 4K look. Camera: Follow the storyboard camera angles exactly (wide shot, medium shot, close-up, extreme close-up, top-down, close-up, wide shot). Important: Treat the uploaded storyboard only as a reference. Never animate the storyboard page itself. Recreate every scene from scratch in full 3D animation. Do not show storyboard borders or text.

This is the remix link: yiha.ai/create?remix=0…

@ yiha.ai created with this prompt: 1990年代欧美家庭录像风格，一段真实的家用摄像机拍摄视频，地点在法国巴黎河岸，明显让人感觉是塞纳河边的夏日下午，有石阶、河岸步道、围观的人群和普通游客。整体必须像1990年代普通人随手拍下来的 home video，而不是现代电影镜头。 画面质感要复刻90年代消费级家用摄像机：不要夸张复古滤镜，不要太脏太重的VHS故障效果。整体色调轻微褪色，低对比度，颜色偏淡，天空略微发白，高光轻微过曝，带有自然的夏日阳光泛白感，像被太阳晒过的旧录像。画质柔和、略微发糊，不锐利，有轻微软焦、轻微动态模糊和非常轻的磁带质感。镜头是远距离手持观察视角，像站在人群中或河岸对面随手拍摄，主体人物在画面里占比不大，环境信息很多，构图随意，轻微晃动，偶尔有笨拙的小幅变焦。 画面中，一位普通的欧美中年女人站在塞纳河边低矮石阶或小码头边缘，穿着很有1990年代感的复古连体泳衣。她不是专业运动员，更像普通游客或朋友。周围一群朋友和围观的人拍手、大笑、起哄，齐声鼓励她跳下去，喊“go! go! go!”、“come on!”. 女人先有点犹豫，低头看河面，回头朝人群笑一下，像在确认自己是不是真的要跳。随后她突然鼓起勇气，向前小跑几步，从河岸边一跃跳进河里，动作夸张、笨拙但很有喜感。她重重落水，炸起巨大的水花，水花溅到岸边围观的人。摄影者一边笑一边跟拍，镜头因为激动而轻微晃动，并短暂失焦，然后重新找到主角。 水花过后，女人从水里浮起来，笑得很开心，游向岸边石阶并慢慢爬上来。一个站在旁边的朋友递给她一瓶酒或玻璃瓶可乐。她接过来，直接喝一口，然后得意地举起瓶子。周围人继续大声欢呼、鼓掌、大笑，把她当成刚刚完成壮举的英雄一样庆祝。 只保留自然现场声音，不要背景音乐：人群起哄、笑声、欢呼声、入水声、河水环境声、远处城市环境声。整体重点是真实、自然、粗糙、偶然、好笑，像一段从1990年代游客录像带里翻出来的巴黎河岸名场面，不要现代电影感，不要广告感，不要过度做旧。

This is the remix link: yiha.ai/create?remix=f…

@ yiha.ai created with this prompt: text[Subject: Solo snowboarder in matte black tactical winter gear] :: [Kinetics: Extreme downhill velocity, triggering a massive powder avalanche behind him] :: [Environment: Alpine peak, sheer cliff face, airborne ice crystals] :: [Lighting Rig: Harsh midday alpine sunlight, blinding snow reflection, high-contrast shadows] :: [Camera Optics: 14mm Ultra-Wide, infinite focus, f/8] :: [Camera Support: FPV Drone tracking from behind, aggressive banking, violent camera shake on impact] :: [Seedance Parameters: --ar 16:9 --motion-blur heavy --shutter-angle 90 --temporal-lock 10]

Which building do you like the most?#transformers #miniatures #landmark

what U want to see next?#transformers #miniatures #landmark

LMAOO I’m obsessed with this voice 😭 Which one’s your fav? #transformers #miniatures #landmark

This is the remix link: yiha.ai/create?task=75…

@ yiha.ai created with this prompt: A single continuous handheld handycam shot in slow motion, drifting and weaving organically through a completely frozen party scene, every person suspended mid-movement like a living diorama. The shaky camera circles and floats slowly. Single seamless slow-motion take.

This is the remix link: yiha.ai/create?remix=c…

@ yiha.ai created with this prompt: 15 seconds, 16:9. Main subject from @ Image1 — lock her completely. Face, skin tone, body, hairstyle, and outfit must remain perfectly identical throughout the entire video. She wears a sleeveless green-and-white striped ribbed knit mock-neck top with a red-and-white striped collar, medium-wash loose straight-leg high-waisted blue jeans, and simple white low-top sneakers. No bag, no shoulder strap, no accessories except subtle natural makeup. Long straight dark brown hair with a center part, softly moving in the breeze. Korean woman with a modern, natural K-pop visual. The entire video takes place in an authentic hillside residential neighborhood in South Korea, similar to the old residential districts of Seoul, Busan, or Incheon. The streets are narrow and steep with frequent concrete stairways and sloping roads connecting different elevations. Small detached homes and low-rise villas are tightly packed together along the hillside. Exterior walls are painted white, beige, faded pastel, or exposed concrete, with stainless steel railings, rooftop water tanks, satellite dishes, air-conditioning units, security bars on windows, narrow alleys, retaining walls, utility poles, dense overhead power lines, small community mirrors at corners, and modest front gates. Flower pots, drying laundry, and neatly arranged plants sit outside many homes. The neighborhood feels distinctly Korean, quiet, lived-in, and residential, with layered houses climbing the hillside. No shops, advertisements, or commercial districts. Camera treatment is the whole point. This needs to look like a friend casually filming on a modern smartphone with no preparation. Natural handheld movement with subtle shake, spontaneous reframing, occasional focus breathing from continuous autofocus, realistic exposure adjustments, slight rolling shutter during faster movements, and imperfect framing where the subject occasionally drifts toward the edge of the frame. Crisp modern smartphone image quality with realistic HDR, accurate colors, natural contrast, and clean detail. No vintage look, no DV camcorder artifacts, no VHS texture, no retro grading, no film emulation. She starts sitting on a low concrete curb casually brushing her hair back with both hands, smiling naturally as the morning breeze moves her hair. The camera slowly steps closer while struggling briefly to keep focus. Then the camera follows her into a narrow residential alley where she crouches down and gently feeds a friendly stray cat that walks right up to her. After that she's in the front yard hanging freshly washed clothes on a clothesline while the breeze softly moves the laundry and her hair. Midway she's relaxing on the front terrace holding a coffee cup, quietly watching the neighborhood with a peaceful expression as the camera drifts casually from the side. Then a right-side close-up catches her slightly late as she raises one hand, waves warmly toward som