YouMind
Sign in

Brand / Product Commercial

Explore free Brand / Product Commercial video prompts from YouMind's AI prompt library, grouped under use cases. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

1310 promptsDaily highlights
Seedance 2.5
View full prompt & copy

Create a cinematic, ultra-realistic food video showing chicken biryani preparation in a rustic kitchen. Show onions being sliced, chicken coated in golden yogurt marinade, and spices sizzling in a traditional copper pot over a blue gas flame. Add marinated chicken, fluffy basmati rice, saffron-colored liquid, fried onions, and fresh herbs. Capture bubbling gravy, rising steam, realistic stirring, and natural ingredient movements. End with the lid lifting to reveal beautifully layered golden and white rice with tender chicken, followed by a macro close-up of the finished biryani garnished with fresh mint and lemon. Warm cinematic lighting, detailed food textures, realistic cooking physics, smooth camera movements, appetizing presentation, vertical 9:16, 30 seconds, no text, no logos, no watermark.

Generate video
Seedance 2.0
View full prompt & copy

Create an ultra-realistic cinematic miniature adventure featuring a tiny athletic woman navigating an enormous everyday world. She runs across a desk, climbs a giant glass jar, explores piles of colorful fabric, scales hanging clothes, and navigates oversized household appliances. Show her climbing a massive bottle cap, crawling beneath a washing machine, and crossing a miniature obstacle course. Emphasize the dramatic contrast between her tiny human scale and gigantic objects. Warm cinematic lighting, realistic textures, shallow depth of field, macro photography, smooth tracking shots, natural human movement, soft shadows, photorealistic details, creative storytelling, premium commercial aesthetic, vertical 9:16 format, 4K quality.

Generate video
Claude Opus 5.5
View full prompt & copy

Reverse engineer [product] from these reference images: 1. Write down the proportions and list every visible part with the frame it appears in. 2. Build it in three.js with each part as a separate mesh. 3. Label every part with what it does and a confidence level. No frame, no claim: anything not visible is marked unknown. 4. Timeline: assemble, move, explode the parts with labels, reassemble. 20 seconds. 5. Use a deterministic render(t), render 30 fps frames and stitch them with ffmpeg. Show me the parts list with frames before writing any code.

Generate video
Seedance 2.5
View full prompt & copy

Create a 30-second, HORIZONTAL 16:9 ultra-realistic live-action comedy on a tree-lined American residential street. TWO drivers compete for ONE remaining parking space: a smug man in a black BMW takes it first, but a blonde woman in a silver Tesla uses downward thrusters to lift her car and park directly ON TOP OF his BMW. End with his stunned reaction and her smiling punchline. REFERENCE ASSIGNMENT REFERENCE IMAGE 1 — TESLA DRIVER: Use this image for the blonde woman's facial identity, hair, visible clothing, and necklace. She drives the Tesla. REFERENCE IMAGE 2 — BMW DRIVER: Use this image for the man's facial identity, pointed ears, gold tooth, blonde braids, black cap, and black hoodie. He drives the BMW. His hands hold no tray or food container. REFERENCE IMAGE 3 — TESLA: Use this image for the silver Tesla's exact exterior design, proportions, wheels, glass canopy, body panels, rear light bar, and rear nozzles. If it is a collage, its panels show different views of ONE car, not multiple cars. REFERENCE IMAGE 4 — LOCATION: Use this image for the American street, brick apartment building, trees, sidewalk, parked vehicles, and the ONE empty parking bay. Keep these assignments separate. Do not swap the drivers, transfer facial features between them, or use the portrait backgrounds as the location. MAIN SUBJECT TESLA DRIVER: An adult blonde woman matching REFERENCE IMAGE 1. Long, loose blonde hair with darker natural roots, a centre part, and soft, slightly tousled waves falling over her shoulders. Light blue eyes, naturally arched eyebrows, long eyelashes, an oval face, softly defined cheekbones, a straight nose, and full pink lips with subtle gloss. Warm, lightly tanned skin with natural texture and a gentle rosy flush across her cheeks. Minimal natural-looking makeup. Relaxed, confident expressions and a subtle, playful smile. She wears the SAME fitted white ribbed tank top with narrow shoulder straps and a scoop neckline, made from opaque fabric. A delicate silver necklace with a small round clear-stone pendant rests against her upper chest. Her long hair, white tank top, and necklace remain clearly recognisable in her close-ups. Do not add a jacket or change her outfit. BMW DRIVER: An adult man matching REFERENCE IMAGE 2. A broad face, fair skin with a slightly flushed complexion, hazel eyes, light eyebrows, short dark facial stubble, a prominent nose, distinctive pointed ears, and ONE visible gold upper front tooth. Bleached-blonde hair with a short fringe and TWO long braids hanging over his chest, secured with black hair ties and ending in loose blonde tufts. He wears the SAME faded black baseball cap with a curved brim and an upright tuft of blonde hair protruding through the top. He wears a loose black pullover hoodie made from thick, opaque cotton, with black drawstrings, ribbed cuffs, and a front kangaroo pocket. The hood rests behind his neck. His pointed ears resemble convincing practical prosthetics with realistic skin texture. Preserve his distinctive appearance without cartoon exaggeration. His expression begins cheeky and self-assured, then changes to wide-eyed disbelief. His hands operate the steering wheel naturally. No tray, takeaway container, food, or handheld prop. Both drivers remain in their original LEFT-HAND driver's seats, wearing seat belts throughout. VEHICLES: The Tesla matches REFERENCE IMAGE 3: silver-grey angular wedge-shaped body, low wide stance, dark glass canopy, sharp metallic body panels, dark wheels, continuous red rear light bar, and FOUR circular rear-facing nozzles. The downward lifting jets originate beneath the chassis. The FOUR rear-facing nozzles remain fixed and do not rotate or move. The BMW is ONE glossy black sedan with silver alloy wheels, a closed opaque metal roof, and American-format licence plates. Preserve both vehicles' models, dimensions, paint, wheels, interiors, and structural details throughout. LOCATION AND HEIGHT Match REFERENCE IMAGE 4 closely. An American residential street beside a red-brick apartment building with dark metal fire escapes, sash windows, a recessed entrance, black iron railings, concrete sidewalks, and mature leafy trees. Foreground: broad asphalt street, subtle cracks, scattered dry leaves. Middle ground: the marked parking row and its parked vehicles. Background: sidewalk, trees, railings, and the brick apartment building. EXACTLY ONE marked parking bay is empty. Every other bay is occupied. The empty bay fits ONE normal car only. Parked cars face nose-first toward the sidewalk, with their rear ends facing the street. Keep the space directly above the empty bay free of low branches or other obstacles. Both story vehicles approach the empty bay in the SAME direction along the street. The BMW is slightly ahead and nearer the parking row. The Tesla is slightly behind and alongside it. Both drivers can see the space and each other. After the BMW parks, the Tesla aligns behind it, facing the same sidewalk. During flight, the Tesla rises until its lowest point clears the BMW roof by approximately 0.5 metres BEFORE moving forward. CAMERA AND LOOK Photorealistic live-action comedy: natural skin, believable expressions, textured clothing, automotive glass reflections, metallic paint, rubber tyres, and visible vehicle weight. One consistent soft overcast afternoon. Natural colours, soft shadows, muted contrast, restrained handheld movement, faint sensor noise, and subtle autofocus adjustments. Keep the location geometry readable across cuts. Preserve the position of the empty bay, building, neighbouring parked cars, and trees. Facial close-ups retain recognisable location details through the windows. Use the exact shot lengths below. The short inserts show simple expressions or a pedal press; the complex flight receives ONE uninterrupted 10-second wide shot. During the flight, keep the complete Tesla, complete BMW, receiving roof, road, and neighbouring cars visible together. Never let vapour obscure the entire action. No glossy beauty lighting, artificial rim light, heavy grading, visible camera operator, or filming equipment reflected in glass. CONTINUOUS STORY 00:00–00:03 — ONE SPACE, TWO DRIVERS Wide three-quarter street view. Begin with BOTH cars already rolling slowly toward the ONE empty parking bay. The empty space is clearly visible between the parked cars, with the brick building and trees behind it. Both vehicles slow as their drivers notice the space. The BMW has a slight positional advantage. The Tesla stays slightly behind and alongside it. Establish enough separation for the BMW to turn without touching the Tesla. 00:03–00:05 — HIS SMUG SMILE Close-up through the BMW driver's side window. The reference man glances toward the blonde woman, then toward the empty bay. He gives a smug, competitive smile, briefly revealing his gold tooth. Keep his pointed ears, blonde braids, black cap, and upright hair tuft consistent with REFERENCE IMAGE 2. No dialogue. 00:05–00:06 — THE ACCELERATOR Tight close-up inside the BMW footwell. His RIGHT foot, wearing a plain black sneaker, presses the accelerator decisively. Show clear shoe-to-pedal contact and the pedal moving down. The engine rev rises immediately. 00:06–00:10 — HE TAKES THE SPACE Medium-wide exterior shot showing the BMW, the parking bay, and the waiting Tesla. The BMW surges forward with ONE brief tyre squeal and turns into the empty bay. Show the complete movement: accelerate, turn, straighten, brake, and stop fully between the white lines. No prolonged burnout or drifting. The BMW does not touch the adjacent cars. The BMW has now occupied the ONLY empty parking space. It stays stationary for the rest of the video. The Tesla waits in the street behind it. 00:10–00:15 — HER CONFIDENT ANSWER Close-up through the Tesla driver's side window. The blonde wom

Generate video
Claude Opus 5.5
View full prompt & copy

you don't need After Effects to sell launch videos anymore 16 steps to run your own motion design studio on Claude Opus 5.5 + Remotion and get paid for product promo clips one product action in. a finished launch clip, a client package and a reusable library out the roadmap: 01 plan the shot pick one feature → pull the key frames → collect logo, screens, font → write the brief 02 build the film set up Claude + Remotion → map every event to a frame → animate the opening → show the product doing its thing 03 polish the film hold text long enough to read out loud → sync sound to every click → check each still → fix one issue per revision 04 turn it into a studio render the MP4 → pack clip + cover → pitch the first client → save what worked the loop: brief → code → preview → small fix → render → review → reuse what you sell first: one 20-second launch clip, one cover, one round of revisions every approved entrance, cursor path and text card goes into your library, so the next client starts from parts, not from zero

Generate video
Seedance 2.0
View full prompt & copy

Generate an 8-second seamless loop orbiting video based on the uploaded product reference image. The subject is completely frozen; the product does not rotate. The camera orbits 360 degrees around the subject along a horizontal circular track at a constant speed, height, and distance. From 0–2s: front to right side. From 2–4s: right side to back. From 4–6s: back to left side. From 6–8s: left side back to front. At the 8th second, precisely return to the starting camera position and composition for a seamless loop. Prohibit push/pull, zoom, shake, jump cuts, subject rotation, or part deformation. Keep lighting, materials, background, and reflections continuous and consistent. No subtitles, text, watermarks, or narration.

Generate video
Seedance 2.5
View full prompt & copy

STYLE: Photorealistic live-action miniature-person VFX, cinematic macro photography, ultra-shallow depth of field, realistic physics, dynamic handheld camera, dramatic lighting, detailed textures, premium viral commercial aesthetic, 4K. Create a 30-second cinematic adventure featuring one athletic miniature woman at approximately 1/5 scale, wearing a pastel-blue sleeveless top, dark shorts, and tiny white sneakers. Maintain consistent face, hairstyle, outfit, body proportions, and scale throughout. She climbs a giant vacuum cleaner as it suddenly switches on, battling powerful suction and swirling dust. She races between enormous furniture legs, dodges a collapsing bedsheet, slides down a giant pillow, and runs across an avalanche of falling clothes. Using a dangling shirt sleeve as a rope, she swings onto a dresser just as the vacuum rushes beneath her. Finally, she lands triumphantly on a clean patch of floor, only for a giant sock to drop beside her. She looks up in disbelief as the camera pulls back to reveal the enormous bedroom. Use dynamic macro tracking, dramatic low angles, realistic fabric physics, detailed dust particles, natural shadows, strong foreground parallax, believable human movement, seamless transitions, and cinematic lighting. SFX: Vacuum roar, rushing air, tiny footsteps, fabric rustling, clothes tumbling, dramatic whooshes, landing impacts, and playful suspenseful music. NEGATIVE: Cartoon, anime, toy-like CGI, plastic skin, inconsistent character, changing outfit, distorted anatomy, duplicated limbs, inconsistent scale, floating objects, impossible physics, excessive motion blur, narration, subtitles, text, logos, watermark.

Generate video
Claude Opus 5.5
View full prompt & copy

Build "Gummy Bears" - a single self-contained HTML file (three.js from a CDN is the only dependency): a handful of translucent gummy bears on a white table that you can grab, stretch, squash, throw and pour. The bears - Classic gummy bear silhouette: round head with two ears, short snout, plump body, stubby arms and legs, tiny molded eyes and nose - Every part melts smoothly into the next - build the body as an implicit surface (metaballs / marching cubes), not separate spheres - Material: real gummy candy. Translucent with transmission and refraction, colored light absorption that gets deeper in thick parts, glossy clearcoat with sharp highlights - Colors: cherry red, orange, lemon yellow, apple green, clear pineapple - Soft colored shadow under each bear, tinted by the bear's own color Physics (this is the whole point - it must feel like jelly, not plastic) - Each bear is a soft body: mass points for head, ears, snout, body, belly, hands and feet, held together by volume-preserving shape matching - Limbs and neck are rendered as stretchy strands between points, getting thinner as they stretch - Grab any part and pull: it stretches like rubber, the rest of the bear leans after it, on release it snaps back with a damped wobble - Pull the head up: the neck stretches, the body follows, on release the bear squashes and hops - Press down on the head: the bear pancakes, bulges sideways, then launches itself back up - Throw a bear: it flies, squashes on landing, bounces and pushes other bears out of the way - Bears collide with each other and never pass through one another - Idle bears do small random hops with squash and stretch - "Pour more bears" drops a handful from above into a wobbling, jiggling pile UI - Editorial product-page style on a white background. Large italic serif title "Gummy / Bears.", a short subtitle, a minimal card on the right with flavor swatches, a wobble slider, live "Stretch" and "Bounces" readouts and a "Pour more bears" button - A subtle circular cursor that grows while grabbing - ACES tone mapping, environment reflections, soft key and back light. Smooth 60fps

Generate video
Claude Opus 5.5
View full prompt & copy

<role> you are a principal motion designer and real-time graphics engineer. you make product launch films entirely in three.js, every frame code, to the standard of the brand's own films. you prove quality with measurements and independent critics, not adjectives. </role> <brief> - the product, and the 3-5 facts the film may state (verbatim, nothing invented) - the reference film to beat - length, aspect and resolution - never show: [logos, people, footage you don't own] </brief> <study> read the reference frame by frame and turn it into numbers: cut rhythm, camera speeds, the hero motion curve, type size and timing, stage colour. those numbers are the bar. measure it, never copy it. </study> <build> - storyboard first: one table of time, shot, what it proves and the cut out. 2-3 s per shot, and frame 0 is already the money shot - one seek clock: every pixel is a pure function of time - build every element (the device, its screen ui, each shot, the type) alone in its own lab before it joins the film - the screen ui is code, the type is drawn on canvas, and every threshold is a crossfade (hard ones flash for a frame) </build> <loop> - builder and critic are always separate agents. the critic starts fresh every round, judges the rendered frames against the reference, scores them and names the single biggest gap. the builder fixes only that - blind test: mix your frames with the reference's. if a judge can tell which is which, it isn't done - wow gate: split the film into 3 s windows. every one must be a yes </loop> <sound> - one real track, lined up so its own final hit lands on the end card and played as one continuous piece. cut on its beat - a clean, real sound on every small move, with the hero moments clearly audible - music quiet (about -34 lufs), and always a music-only version </sound> <qa> render at 60fps and measure frozen frames, one-frame pops, black frames and loudness. then watch it like the client would: empty space, text over text, labels that lie, shots that linger. </qa>

Generate video
Loading more prompts

FAQ

Where do YouMind prompts come from?
YouMind curates high-signal AI prompt examples from creator communities and public creative workflows. The library focuses on prompts that are useful to inspect, reuse, and adapt.
How are video prompt categories organized?
Video prompts are grouped into use cases, styles, and subjects. Use cases cover the production goal, styles cover motion or rendering language, and subjects describe the main scene or entity.
How are prompts assigned to categories?
YouMind uses AI to analyze each video prompt, its title, metadata, and generated result when available, then assigns the closest categories. Editors can refine categories as the taxonomy evolves.
What is YouMind?
YouMind is an AI workspace for turning research, ideas, and creative references into usable outputs. The prompt library is one public part of that workflow, built to help creators learn from strong examples faster.