Cinematic prompts for Kling, Veo and Runway — shots, motion, characters and camera direction.
Search within Video AI only — titles, summaries, use cases, models and tags.
View all 48 promptsBrowse by Use Case
Pick the use case closest to what you're working on.
Browse by AI Model
Open the model hub to see how each one handles this kind of work.
All Prompts
Filter by use case, model or difficulty — every prompt in this category, on one page.
Showing 1–12 of 48 prompts
This prompt guides DTC brand teams in scripting a 30-second marketing video. It structures the narrative around a customer problem, product solution, and social proof, ensuring brand consistency and funnel awareness. The output includes specific scene breakdowns and platform cut specifications for efficient production.
DTC home & kitchen marketers: Generate a full 45-second video demo package for a kitchen gadget. Includes script, shot list, on-screen text, captions, and b-roll, emphasizing authentic, messy, real-world usage on a busy counter.
Generate a 60-second marketing video script for B2B customer testimonials. This prompt structures the video into key funnel stages: hook, value beats, proof, and a clear call to action, complete with b-roll suggestions and lower third text. It helps B2B marketers quickly produce targeted ad content from longer interviews.
Craft a 30-second video script for B2B SaaS product marketers announcing a new feature. This prompt structures the narrative around a problem-solution arc, demonstrating the 'before' and 'after' states, highlighting key value, and concluding with a direct in-app call to action. Ideal for driving feature adoption.
Generate a 60-second video demo script for an AI feature. It includes shot lists, on-screen text, and captions, focusing on a realistic before/after to avoid overclaiming. This ensures product credibility and clear communication of value to the audience.
This prompt guides sales enablement teams to generate a 2-minute product demo video. It outlines a core workflow walkthrough, featuring an AE presenter and on-screen highlights, designed to equip sales reps with consistent, value-first content for prospect engagement.
Create a 60-second event recap sizzle video for marketing, highlighting 8 key moments with ambient audio and on-screen branding. This prompt helps structure the video for a specific funnel stage, ensuring brand consistency and a clear call to action to boost post-event engagement.
This prompt guides product marketing teams in creating a 15-second launch teaser video. It specifies a silhouette reveal, a core value proposition beat, and a final frame launch date. The structure builds anticipation and ensures brand consistency, delivering a funnel-aware asset for new product introductions.
This prompt helps AI filmmakers create a nuanced, intimate two-shot scene set in a diner booth. It specifies camera movement, lens choice, lighting, wardrobe, and score cues to achieve a character-driven, atmospheric film look, ensuring emotional depth and visual storytelling.
Generate a cinematic rooftop confrontation scene at golden hour. Define shot lists, camera moves, lens choices, lighting, wardrobe, and score cues. This creates a high-stakes, character-driven sequence with a strong film aesthetic, suitable for documentary climaxes.
Generate a detailed production plan for a 4-minute short film scene depicting a tense family dinner. The focus is on non-verbal communication, specific lighting, and a precise four-shot coverage plan to convey underlying emotional conflict without dialogue. This setup is ideal for directors aiming for subtle dramatic impact.
Develop a detailed 6-minute bottle episode scene for a short film. This prompt generates a logline, shot list, character notes, wardrobe, lighting, and score cues for a three-character, single-location turning-point conversation, optimizing for limited production resources.
Featured Prompts
The strongest prompts in this category — copy, tweak and ship.
⭐ Editor's Choice
One prompt we'd ship today. Read why it works, see a preview, and copy it in a click.
Why it works · It treats the prompt as a shot spec — subject, action, camera, lens, lighting, pacing — which is how AI video models actually want to be prompted.
Best use case
Best for video ai workflows where slow-motion espresso pour with anamorphic film look.
Expected output
A short cinematic beat ready to stitch into a longer sequence — with consistent character and motion.
Slow-motion espresso pour with anamorphic film look.
Collections
Curated groups for different skill levels and goals.
Related Categories
If this category is useful, you'll probably like these too.
Video AI prompts translate a director's vision into the exact language Kling, Veo and Runway understand: lens, motion, light, mood and pacing.
Each prompt is a complete shot spec — from subject and action to camera, lighting and film stock. Drop one in, swap a few details, and get usable footage in minutes.
If you're new to AI video, start with the cinematic single-shot prompts before moving to multi-shot character consistency.
Editorial
Welcome to the Video AI hub. You'll find 48 video ai prompts organised by use case, ranked by quality and tagged with the AI models that handle each task best. The collection is curated, not generated — every prompt has been written by humans, tested against real workflows and refined based on what actually ships.
These prompts are built for filmmakers, motion designers, social-video creators and brand teams producing AI video at scale. They work across the major AI models — ChatGPT, Claude, Gemini and the leading image and video generators — and they hold up whether you're prompting in a chat window, an editor extension or a workflow tool. Use these for ads, social shorts, product loops, brand stories and concept reels — single shots or stitched sequences.
Why these prompts work: each one starts with a clear role, names the audience or scene, defines the output format and adds 2–3 hard constraints. That structure is what separates a vague AI answer from a usable one. The library is curated so you don't have to test 30 versions of the same prompt to find the one that actually performs — that work is already done.
Expect short cinematic beats with consistent character, motion and lighting — ready to stitch into longer sequences. You'll occasionally want to regenerate or refine, especially the first time you use a prompt with your own context. Treat each prompt as a starting structure: the variables and constraints stay, the topic and tone become yours.
Read each prompt before you copy it. Swap the placeholders for your real audience, product and constraints, and add one or two video-specific details from your own brief. The prompts here are designed to be edited — the more context you bring, the stronger the output.
If you're new to AI prompting in video ai, start with the featured prompts at the top of this page — they're the highest-leverage, lowest-friction picks. From there, drop into the use-case hubs below to find the exact workflow you need.
Prompt Writing Guide
Six habits that consistently produce stronger AI output. Apply them to any prompt on this page.
Think like a director: subject, action, camera move, lens, lighting, pacing. Treat each prompt as a one-line shot spec.
Static, slow dolly in, hand-held tracking, crane up. Camera language is what makes AI video feel cinematic rather than slideshow-ish.
Repeat the subject's defining details ("the same woman in the red trench coat") across shots so identity holds between cuts.
Slow-motion, real-time, time-lapse. Pacing changes meaning more than any visual tweak.
Match cut, whip pan, smash to black. Stating the transition makes multi-shot sequences feel intentional.
Most weak renders are lighting problems, not subject problems. Change the light first and most issues disappear.
Best Practices
Apply these in every prompt on this page. Small habits, outsized improvements in output quality.
Subject, action, camera, lens, lighting, pacing. Six elements, one line.
Copy-paste the wardrobe and identity description between shots.
Most weak renders are lighting problems. Fix the light first.
Multiple 4–8s beats outperform one long generation every time.
Avoid These
The same handful of mistakes are responsible for most weak AI output. Catch them before you hit send.
Video needs motion. State what moves, how fast, and where the camera goes.
Identity drift wrecks sequences. Repeat the defining details every time.
Without speed cues you'll get a default mid-tempo clip every render.
Lens choice changes the whole feel. Always specify focal length or shot type.
Most AI video models excel at 4–8 second beats. Stack short shots instead.
Pro Tips
Side-by-side rewrites that show what separates a weak prompt from a great one.
Instead of
“A car driving.”
Use
“Cinematic 6-second shot. A vintage red Porsche 911 drives through a misty mountain pass at dawn. Camera tracks alongside on a low-angle dolly, 35mm lens, slight motion blur, soft golden light breaking through the fog. 16:9.”
Why it works: Subject, motion, camera, lens and lighting are pinned.
Instead of
“A person dancing.”
Use
“5-second hand-held shot of a young dancer in a sunlit empty studio, slow rotation, white tank top, 50mm lens, soft side window light, real-time pacing. Hand-held shake should be subtle.”
Why it works: Shot length, lens and camera behaviour are explicit.
Instead of
“Aerial city shot.”
Use
“8-second drone shot, slow forward push over Manhattan at blue hour, 24mm lens, lights of the city beginning to glow, soft haze, cinematic 2.39:1 letterbox, photoreal.”
Why it works: Time of day, lens and aspect ratio shape the look.
Instead of
“A product video.”
Use
“4-second studio shot of a matte black smartwatch rotating slowly on a turntable, soft top key light, subtle rim light, 85mm macro lens, sharp focus on the dial, white seamless background, 1:1.”
Why it works: Camera move and lighting setup keep the focus on product.
Instead of
“A cinematic scene.”
Use
“10-second locked-off shot, two characters facing each other across a small wooden table in a dimly lit diner, single overhead pendant light, 35mm lens, anamorphic flare, slow zoom in, moody jazz lighting.”
Why it works: Stationary camera + slow push communicates tension.
From the blog
Guides, playbooks and case studies from the Prompt InFlow blog.
FAQ
Common questions about using this category of prompts.
Related searches
Popular searches related to this page. Each one links to the closest matching prompt library.
Browse dozens of curated prompts optimized for modern AI models.
