Template for simple testing
Create a 10-second video of [subject] in [setting]. The scene should feel like [style/material]. Use [camera movement]. The motion should be [slow/energetic/cinematic]. Lighting should be [lighting]. Keep the atmosphere [mood].
Papercraft
Create a 10-second one-continuous-shot video of a tiny paper fox walking through a layered papercraft forest at sunrise. Use visible cut edges, folded trees, handcrafted shadows, a slow camera push-in, soft golden lighting, and a whimsical mood.
Origami
Create a 10-second video of an origami crane unfolding on a wooden table and lifting into the air. Show crisp folds, elegant paper texture, gentle camera tilt, soft window light, and a serene poetic mood.
Claymation
Create a 10-second claymation scene of a small explorer crossing a rocky hill while clouds slowly move overhead. Use hand-modeled textures, slightly imperfect stop-motion timing, a locked-off camera, warm afternoon light, and a cozy adventurous mood.
Plush world
Create a 10-second video of a plush toy astronaut floating through a soft fabric moon base. Show visible stitching, fuzzy textures, slow drifting movement, a smooth camera glide, and a cozy magical atmosphere.
15 second epic fantasy action video. One single continuous shot, no cuts, no edits, no jump in continuity. Scene: A moonlit jungle temple kingdom, giant trees, glowing flowers, blue mist, ancient stone bridges, waterfalls, and silver moonlight shining through leaves. Main subject: A fierce female fantasy warrior in elegant dark armor riding a massive black moon panther with glowing silver markings and jeweled armor. Camera: Begin with a high sweeping aerial shot over the jungle canopy, then dive through vines and glowing petals, landing beside the rider in a fast side-tracking shot. Action sequence: The moon panther races across a giant tree-root bridge, jumps over a broken section, lands on mossy stone, then makes a second larger leap over a glowing ravine filled with fireflies. A winged serpent attacks from the right, snapping close to the rider. The warrior blocks with twin curved blades, twists low on the saddle, and slashes once as the serpent passes beside her. The panther keeps sprinting through falling leaves and temple ruins, then launches toward the top of a tall moonlit pyramid. Slow motion moment: At the peak of the final jump, briefly slow the motion. Show silver mist, fireflies, petals, and blade sparks floating in the air. Final beat: Motion returns to normal as the panther lands on the pyramid. The warrior delivers a final double-blade strike to the serpent. End with a wide shot behind her, revealing the glowing jungle kingdom under the moon. Visual style: Premium cinematic fantasy, silver moonlight, emerald jungle, glowing blue mist, elegant female warrior energy, fast action, magical beauty.
Create a luxurious 15-second cinematic advertisement video for "The Erosion Bench" by Strata Form.
Strictly use the two uploaded reference images as the primary visual references. Replicate the exact sculptural wavy form, layered sandstone-like strata texture, warm beige/cream stone color palette, ergonomic contours, and premium product photography lighting/style from both images with maximum fidelity.
Overall style: High-end premium furniture commercial, photorealistic, serene and timeless. Soft dramatic natural lighting with gentle shadows that beautifully highlight the carved layers and fluid forms. Warm earthy tones, shallow depth of field, elegant smooth camera movements (slow orbits, gentle dollies, and pushes). Professional cinematic color grading exactly matching the references.
Video structure (exactly 15 seconds, multi-shot):
0–4 seconds: Elegant slow camera orbit and push-in around the full Erosion Bench in a tranquil minimalist outdoor public plaza with soft morning light. Start close on the beautiful layered strata texture and flowing carved curves, then slowly reveal the complete sculptural form. Subtle text fades in gracefully: “TIME CARVED FORM”
4–9 seconds: Smooth montage of close-up details gliding across the bench’s surface — layered striations, soft water-carved edges, and ergonomic seating. Gentle animated light reflections and water-like glints evoke millions of years of canyon erosion. Text overlay appears: “A public bench sculpted by the language of water and stone.”
9–13 seconds: Three diverse people (young adult, couple, and older person) comfortably sitting together on the bench in a natural, relaxed way. Show the ergonomic comfort and shared social experience. Camera gently circles them.
13–15 seconds: Clean final wide shot of the bench. Elegant brand text appears: “STRATA FORM” “EROSION BENCH” “www. strataform. design”“Geologically Inspired • Civic Durability”
End on a serene, timeless note with a slow fade.
Mood: Tranquil, premium, nature-inspired, enduring, and quietly powerful. Ultra-high production value, 4K, no fast cuts, perfect reference adherence.
1 person on camera, 12 seconds, top-tier car advertisement quality, cinematic film-level shots, real speed pressure, seamless space-time transitions, character consistency front to back, stable frame, layered emotional escalation.
[0.0-4.0s] Ultra-low macro angle locked to the floor, warm golden afternoon sunlight illuminating a cream shag carpet, dust particles floating, vintage Kodak warm-yellow film tone. Only the small childlike hand of the subject is visible, violently shoving a blue Porsche toy car forward. Camera hugs the toy car's nose in a high-speed tracking shot simulating a real racing POV, speed escalating relentlessly, childhood imagination fully ignited.
[4.0-5.5s] Toy car rockets into the dark shadow under the sofa, light cuts instantly, carpet texture stretches into radial speed trails, entire frame consumed by darkness. Shadow acts as a seamless match-cut portal, a warp from childhood to present reality.
[5.5-9.0s] Engine roar detonates from black. Real red Porsche 911 GT3 screams out of darkness onto a cold gray circuit. Sharp overhead light, razor paint reflections, tires kicking heat haze and light smoke. Camera holds the exact same ground-level tracking angle as the toy segment — as if the toy scaled directly into a real car. Physically visceral speed, visually devastating.
[9.0-12.0s] At peak speed, subject releases the steering wheel — hands rise. Car begins to vibrate violently, blue paint cracking like a mechanical shell. Body panels unfold one by one: hood splits into wings, doors pivot into thrusters, wheels retract into the frame. Track falls away as the car lifts off the asphalt. Subject sits in an open cockpit, wind tearing at jacket and hair. Camera pulls back in a rapid epic drone shot, revealing a full blue flying robot blasting into the sky, leaving a glowing light trail across the late afternoon horizon. Final freeze: flying robot silhouette against the setting sun.
Negative: blur, low resolution, character deformation, multiple people, hand errors, wrong car model, jump cuts, hard transitions, lag, dropped frames, plastic texture, fake car feel, excessive VFX, animated look, cheap filter, unstable face, inconsistent age, cartoon robot, CGI-only feel, photorealistic breaks
been testing a different workflow lately using tapnow. what makes it interesting is how it structures the entire process from idea → visuals → final video. instead of jumping between tools, you can actually build everything in one flow and refine it step by step like a real production pipeline. for the visuals, i'm using seedance 2.0 which is currently one of the strongest models for photoreal, human-centered video. but quick note — seedance 2.0 is currently only available in selected regions and requires a verified corporate email to access. still, the direction is clear: AI video is moving from "generation" → into "directing". also, they just launched a global challenge called "10,000 Parallel Universes" with a $200K prize pool. if you're exploring cinematic AI workflows, this is actually a good place to test ideas and push concepts further.
A tight, intimate two-shot at the bar in a dimly lit sci-fi western saloon with warm amber lighting, soft haze, and shallow depth of field. The Japanese woman in a red corset leans slightly closer across the bar toward Cal in a black pinstripe suit, fedora, and dark glasses. The camera remains steady at eye level, capturing both faces in profile with soft bokeh lights glowing in the background. She studies him with quiet curiosity, her voice low and smooth as she asks in Japanese: 「お名前は何ですか？」A subtle pause. Cal remains perfectly still, then slowly tilts his head a fraction toward her, his metallic face catching the warm light. His tone is calm, controlled, and emotionless as he replies in Japanese: 「重要じゃない。」Hold the tension for a beat as the ambient saloon noise hums softly underneath.
Shot 1: Weapon Clash · Explosive Opening
Authentic Fog Hill of Five Elements Chinese animation style, sharp hard-edged ink lines, high-contrast red-black dark palette.
Two warriors wield dual weapons and collide head-on—long weapon sweeping, short blade thrusting—locking at the instant of impact. Sparks burst like tearing metal, ink-like shockwaves radiate outward, robes are violently lifted by the force, hair stands on end.
Veins bulge along both arms, muscles tense under full exertion, their strength perfectly equal—matched in power, evenly balanced, each with their own edge.
Camera: low-angle high-speed forward tracking shot, slight camera shake, impact close-ups, explosive motion lines, sharp Fog Hill of Five Elements-style cinematography.
Shot 2: Afterimage Barrage · High-Speed Offense and Defense
Ultimate fluid combat in Fog Hill of Five Elements style. Both fighters erupt into multiple afterimages, dual weapons interweaving through slashes, blocks, deflections, counters, and transitions.
One is fierce and explosive, delivering wide, heavy strikes; the other is agile and unpredictable, slipping in close with gliding footwork and precise thrusts.
Blades graze past bodies, elbows collide, knees strike, feet clash—every move narrowly lethal. Ink-like energy streams coil around the weapons, motion blur maxed out, impact intensity explosive.
Camera: 360° rotating shots, ultra-fast cuts, smooth focus tracking, strong light-shadow contrast, maximum sense of pressure.
Shot 3: Close-Quarters Combat · Combo Explosion
Both abandon distance and engage in close-range slaughter with dual weapons—chop, slash, thrust, lift, smash, sweep, block, and break—combos seamlessly chained together.
Each impact triggers a circular shockwave, the ground fractures, debris scatters, dust and ink energy surge and churn.
Offense and defense switch instantly; blocks and counters occur simultaneously. Neither can overpower the other, the combat rhythm pushed to extreme tension.
Camera: slow-motion impact close-ups, ultra-wide lens distortion, intense camera shake feedback, explosive ink-style visual effects.
Shot 4: Full Aura Release · Ultimate Clash
Both unleash their full power, dual weapons infused with ink-like aura and blazing energy, ultimate techniques colliding head-on.
The fierce fighter delivers a mountain-shattering blow; the agile one launches a lethal piercing strike. The two forces collide directly, erupting into an energy storm, the world shifts color, shockwaves sweep everything away.
The style becomes wild and epic—both sides remain perfectly matched, evenly dominant, overwhelming pressure at its peak.
Camera: epic low-angle wide shot, backlit silhouettes, cinematic depth of field, screen-shaking effects.
Shot 5: Stalemate Freeze · No Victor
The battle halts abruptly. Dual weapons remain locked in deadlock, opposing auras forming a vacuum vortex.
The two stand in confrontation, eyes cold and filled with killing intent, energy surging, dust filling the air.
Perfectly matched, no victor decided, tension held at maximum through deliberate stillness.
Camera: medium shot slow push-in freeze frame, high-end Fog Hill of Five Elements animation quality.
Global Enhancement Keywords (must be included in each segment)
Fog Hill of Five Elements animation-level style, extremely sharp ink lines, intense dual-weapon combat, heavy impact in every strike, blades full of force, powerful hit feedback, evenly matched opponents, each with their own strengths, high-intensity combat, cinematic professional camera work, maximum dynamic effects, Chinese violent aesthetics, no text, animation storyboard, 4K ultra HD, maximum detail, maximum motion fluidity, maximum tension.
Gemini Omni Flash
