YouMind
Sign in

Product

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

Create product videos
883 promptsDaily highlights
Seedance 2.0
View full prompt & copy

Create a cinematic, ultra-realistic luxury watchmaking commercial. Show a skilled watchmaker in a dark premium workshop carefully assembling an intricate mechanical gold watch. Start with close-ups of tiny gears, screws and moving mechanisms, then show his hands precisely placing the delicate components with professional tools. Slowly reveal the complete watch being polished and placed on his wrist. End with an extreme macro shot of the finished watch and its moving mechanical gears. Dark elegant lighting, realistic metal reflections, shallow depth of field, smooth camera movement, detailed craftsmanship, premium luxury advertisement aesthetic, photorealistic 3D animation. No text, logos or watermark.

Generate video
Claude Opus 5.5
View full prompt & copy

<inputs> Ask me for: the one question a user asks my product and its one-line answer, two album covers, a royalty-free song around 110 BPM with a quiet intro and a hard drop (Mixkit, free for commercial use), and my logo for the ending. If I skip any, use the defaults: "is this all code?" / "yes. every frame.", two atmospheric photos, Mixkit "Head Bang". </inputs> <direction> A 22 second square loop, 1440x1440 at 60fps, 2D only, one continuous take. Nothing ever cuts: every scene grows out of the last, and every gesture physically carries the camera into the next world. Every morph glides for 0.8s on cubic-bezier(.45,0,.15,1) and the camera zoom rides the same curve, so shapes change so smoothly you barely notice. Content dissolves in the back half of each glide. One gesture per scene. Look: a warm light stage (#f3f3f0 to #e3e3de), black UI, the app world dark (#121212) tinted from the current album cover, one green accent (#1ed760). Geist for UI, the real macOS pointer, soft layered shadows that grow with the shape's height. Banned: hard cuts, bouncy springs, particles, glows, zooming in and straight back out, holds longer than 1s, anything that looks like a template. </direction> <structure> Beats are the song's, and the press lands on its drop. Generate: the cursor clicks, the pill glides into a spinner, then a check. Chat: the check splits into three typing dots (goo). The left dot flies up into the question bubble and types it, the right one flies down into the reply. Both contract back into dots while gliding in and pour into the middle one. Play: the middle dot bends into a play triangle, point by point. The cursor presses it on the drop: a white button pops in under the click and the dark app floods out around it, so the leftover white becomes the play button. The camera pulls back to reveal the full now-playing screen: big cover, title, heart (liked, fills green), progress, controls, volume. Swipe: the cursor drags the cover sideways, the next track slides in, and the whole app retints from the new cover. Drag: the camera glides to the volume. The cursor drags it to max and keeps pulling: the bar rubber-bands and drags the camera sideways out of the app, tracking the knob across a dark dotted canvas. Chart: the line lands and bends up into a green chart while the number counts up. The volume knob becomes its last point. Dive: the cursor clicks that point and the camera dives into it until the light stage fills the frame. Ending: an "Ask [my product]" button grows out of the light, thins into a line, and the line fans out into my logo (default: the Claude spark, six copies rotating into twelve rays in Claude orange). It folds back into the line, which thickens into Generate. Last frame = first frame. </structure>

Generate video
Seedance 2.5
View full prompt & copy

Create a 30-second vertical 9:16 ultra-photorealistic miniature vintage car restoration time-lapse. A rusty abandoned classic car is restored by hundreds of tiny realistic adult workers inside the SAME miniature workshop. Extreme macro cinematography, shallow depth of field, warm cinematic lighting, realistic metal, paint, leather, glass, dust and tools. Every 2 seconds, show a NEW physical restoration stage: 0–2s: Inspect and dismantle rusty parts. 2–4s: Remove wheels, panels, lights and bumpers. 4–6s: Sand and remove rust. 6–8s: Weld dents and repair body panels. 8–10s: Clean and prepare the metal. 10–12s: Apply primer. 12–14s: Spray glossy deep-red paint. 14–16s: Polish the fresh paint. 16–18s: Rebuild and install engine. 18–20s: Install suspension, brakes and wheels. 20–22s: Install grille, bumpers, lights and chrome parts. 22–24s: Restore seats, dashboard and interior. 24–26s: Install windows and final details. 26–28s: Start engine, test lights and polish the car. 28–30s: Finished vintage car drives out of the workshop. Hundreds of tiny workers must remain continuously visible, performing different tasks simultaneously—carrying, lifting, sanding, welding, painting, polishing, tightening and installing. Every transformation must happen physically and step-by-step. Same car, workshop, scale and lighting throughout. No instant appearance, morphing, teleportation, floating objects, CGI, cartoon, plastic look, duplicated workers, text, logos or watermark.

Generate video
Seedance 2.5
View full prompt & copy

{ "model": "Seedance 2.5", "duration": "10 seconds", "aspect_ratio": "9:16", "objective": "Create a realistic 10-second beauty UGC video from the supplied reference image. The same adult woman casually applies the pink lip product while talking naturally to camera. Keep the shot simple, stable and believable.", "reference_fidelity": { "priority": "HIGHEST", "instruction": "Preserve the woman's face, hair, skin tone, makeup, black tank top, necklace, gray sweatpants, bathroom environment and pink lip product from the reference image.", "continuity": "Keep her appearance and the room consistent for the entire clip." }, "camera": { "style": "real smartphone beauty UGC", "framing": "same waist-up composition as the reference image", "movement": "very subtle natural handheld movement only", "focus": "keep her face sharp and stable", "look": "natural smartphone exposure, realistic skin texture, no cinematic grading" }, "starting_frame": { "instruction": "Start directly from the supplied reference image.", "pose": "She is already holding the pink lip product near her lower lip.", "expression": "relaxed and naturally engaged.", "speech": "Begin speaking immediately." }, "script": { "full_dialogue": "Okay wait, I actually really like this. The color is so pretty, it goes on super easy, and it makes my lips look way better without looking like too much.", "delivery": "Casual beauty creator recommendation. Slightly persuasive but still natural, spontaneous and unscripted." }, "action": { "instruction": "Keep the physical action minimal. She lightly applies the pink lip product, pauses to look at the result, presses her lips together once, then gives a small approving expression.", "hands": "Only animate the visible hand holding the lip product. Do not create another hand, arm or additional limb.", "product": "Keep the pink lip product stable and consistent in shape and size." }, "performance": { "expression": "subtle, confident and pleased", "head_motion": "small natural movements only", "blinking": "normal irregular blinking", "gestures": "minimal", "overall_feel": "real creator casually showing a product she likes" }, "realism": { "skin": "natural pores and skin texture", "hair": "realistic strands and slight natural movement", "mouth": "natural lip movement and accurate speech synchronization", "background": "keep all bathroom objects stable", "continuity": "no object duplication or changing anatomy" }, "negative_prompt": "duplicate hand, duplicate arm, extra hand, extra arm, extra fingers, additional limbs, floating hand, detached hand, malformed hand, fused fingers, duplicated product, additional product, object duplication, identity drift, altered face, changing hairstyle, changing clothing, warped anatomy, warped background, mirror artifacts" }

Generate video
Claude Opus 5.5
View full prompt & copy

Act as a senior motion designer and build a 30-second launch video for [product] in Remotion, entirely in code so I can edit and re-render it: first read my landing page and codebase to pull the real story, copy, colors, font and logo file (trace the logo to SVG so it stays sharp and can be animated), then write the video as one story (why the market matters, why it's painful today, how [product] fixes it, what you get) in 4 to 5 scenes with one short title each, animate everything like a premium product film (kinetic typography word by word, spring easing, smooth camera pushes and pans, depth and glow, elements that build in on the beat instead of just appearing), keep each scene on screen long enough to read, add one soft sound effect for every element that appears and silence otherwise, and end on a memorable animated logo reveal with the tagline and URL, then render it, check the frames yourself and fix anything that overlaps, clips or feels rushed before showing me the result.

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.