by Runway

Runway Gen-4 Prompts

Runway's generation model for filmmakers — the same character, the same world, shot after shot.

imagevideo
All categories3D RenderAbstractAdvertisingAerialAmbientAnimalsAnimationAnimeArchitectureAvatarBlack & WhiteBrightCartoonCharacterCinematicCityscapeClassicalComicCyberpunkDarkDigital ArtDramaticDynamicElectronicEtherealFantasyFashionFolkFoodGame AssetsGothicHip-HopHistoricalHolidayHorrorInfographicJazzLandscapeLo-FiLogo DesignMacroMinimalistMotion GraphicsMusic VideoMysteriousMythologyNatureNeonOil PaintingPeacefulPixel ArtPopPop ArtPortraitPosterProduct PhotographyR&BRealisticRockSci-FiShort FilmSketchSlow MotionSound EffectsSpaceSportsSteampunkStickerStill LifeStreet PhotographySurrealTattooTimelapseTrailerTypographyVectorVehiclesVFXVintageVoiceoverWallpaperWatercolorWhimsical
0:15
Runway Gen-4
*Style:* Ultra-realistic, IMAX-quality, cinematic luxury fashion film, Netflix action-trailer energy, premium color grading, dramatic natural lighting, realistic reflections, shallow depth of field, anamorphic lens flares, dynamic camera movement, 8K HDR, photorealistic skin, high-end fashion editorial aesthetic. **Audio:** No dialogue. Powerful electronic trailer soundtrack with deep bass drops, cinematic impacts, whooshes, footsteps, ambient airport sounds, and subtle risers synchronized perfectly with every cut. --- **0:00–0:02 | Grand Entrance** Ultra-wide establishing shot inside a modern international airport. Automatic glass doors slide open in slow motion as the model confidently enters frame. She wears oversized black sunglasses, premium wireless headphones, an elegant luxury travel outfit, and carries a sleek designer carry-on. Strong cinematic bass hit as the doors fully open. --- **0:02–0:04 | Runway Walk** Fast side-tracking shot. She confidently walks through the terminal with effortless runway energy while pulling her suitcase. Motion blur enhances speed. Dynamic speed ramps. Airport architecture streaks past. Luxury boutique stores glow in the background. --- ### **0:04–0:06 | Fashion Montage** Rapid editorial-style cuts (0.5 seconds each): • Hand grabbing a fresh coffee from a stylish airport café • Boarding pass smoothly flips into her hand • Extreme close-up of a luxury watch catching sunlight • Designer sneakers striking the polished marble floor Every cut lands perfectly on the beat. Flash-frame transitions between shots. --- **0:06–0:09 | Hero Walk** Epic low-angle tracking shot. Golden sunlight pours through enormous airport windows. Lens flares dance naturally. Crowds become beautiful motion blur while she remains perfectly sharp. The camera slowly pushes closer as she walks with complete confidence. --- **0:09–0:11 | Energy Build** Rapid cinematic sequence: • Riding the escalator • Departure board changing flights • Slow-motion hair flip • Adjusting sunglasses • Smooth 180° orbit camera transition Whip pans connect each shot. Bass impacts emphasize every transition. --- **0:11–0:13 | Final Build** Slight slow motion. She walks toward the boarding gate. Long cinematic shadows. Beautiful anamorphic lens flares. Trailer boom as automatic boarding doors begin opening. Camera slowly dollies backward. --- **0:13–0:15 | Signature Ending** Rear hero shot. She walks through the jet bridge toward the aircraft. Just before disappearing, she turns her head and gives a subtle over-the-shoulder glance toward the camera for a single frame. Immediate hard cut to black. Massive cinematic impact sound. Music ends on a powerful bass hit.
Details
0:30
Runway Gen-4
Immersive first-person flying camera perspective, no visible drone or flying device. Designed for a continuous 30-second sequence. The camera launches at extreme speed into a colossal abandoned spaceport at night, skimming only inches above cracked metal flooring and scattered debris as it races through a massive derelict hangar. It snap-rolls between suspended spacecraft, knife-edges past giant dormant engines, dives beneath rusted mechanical arms, and threads through rotating blast doors with razor-thin precision. Without slowing, the camera performs rapid S-turns through narrow maintenance corridors, bursts into a vast launch chamber, corkscrews around towering fuel tanks, wall-hugs along the inside of a gigantic tunnel, then plunges through the hollow frame of a half-assembled starship. Emergency lights begin flickering on one by one, revealing colossal gantries, hanging cables, drifting sparks, and endless industrial architecture swallowed by darkness. The camera power-loops around a reactor core, split-S reverses through a collapsing service shaft, then accelerates into a vertical launch tower, climbing straight upward through concentric rings, steam bursts, and rotating machinery. The ascent becomes overwhelming as the entire station suddenly reactivates below, with runway lights, engine glow, and launch systems illuminating the dead complex. In the final seconds, the camera bursts out of the tower into the upper atmosphere and then into orbit, revealing the entire abandoned spaceport glowing to life beneath, attached to a vast planetary launch network stretching across the surface. Continuous POV shot, no cuts, relentless acceleration, extreme high-speed FPV, aggressive banking, rapid altitude changes, barrel rolls, corkscrews, split-S maneuvers, power loops, realistic inertia, cinematic motion blur, volumetric smoke, sparks, dramatic sci-fi lighting, hyper-detailed environments, blockbuster spaceport VFX, IMAX quality.
Details
0:30
Runway Gen-4
Create exactly 30 seconds of photorealistic 4K third-person video game gameplay inside a small outdoor rabbit enclosure at a countryside petting farm on an overcast morning. It should look like captured footage from a modern stealth game: game-engine rendering, a simple HUD, and smooth controller-style movement. Keep everything grounded and continuous. CHARACTER: Early-twenties East Asian woman with shoulder-length bleached-blond hair (dark roots) half pulled back with a black claw clip, cropped cream knit sweater, dark-green canvas work apron, light-wash jeans, grey rubber boots. A red lanyard with a small brass key is clipped to her apron. Keep her identical throughout. ENVIRONMENT: Grassy fenced enclosure with a dirt path, two wooden hutches, one hay bale, and four rabbits: three grazing in the background and one small black-and-white Dutch rabbit as the target. Realistic fur and natural rabbit movement. HUD: Objective text top-left only. One short button prompt appears when relevant. Nothing else on screen. 0–6s — SNATCHED She crouches by a hutch and unclips the key. The Dutch rabbit hops in, grabs the lanyard in its teeth, and bolts a few meters across the grass. HUD: GET THE KEY BACK 6–16s — SLOW APPROACH She rises into a crouch-walk and follows slowly. When she moves too fast, the rabbit freezes, ears up, then hops further. She stops, waits for it to graze, and continues. 16–24s — GRAB The rabbit drops the key beside the hay bale. She kneels, a "Grab" prompt appears, and she reaches out slowly and picks up the key just as the rabbit looks at her. It sneezes and hops away. HUD: KEY RECOVERED 24–30s — HARD CUT Cut to a frontal shot at the hutch. She opens the feed bin with the key, takes out a carrot, and hands it down to the same rabbit now sitting at her boots. She smiles. HUD: MISSION COMPLETE CAMERA: Single third-person gameplay camera behind and slightly beside her, waist height, lowering as she crouches. Smooth tracking with slight lag. No cuts until 24s, then one hard cut. AUDIO: Birdsong, wind in grass, boots on dirt, rabbit hops, key jingling, soft breathing, a quiet UI chime on each HUD update. No music. RULES: Realistic physics and rabbit behavior. No teleporting, no extra rabbits, no changing her face, hair, outfit, or the key. No anime or cartoon style, no cinematic depth-of-field, no subtitles, logos, or watermarks. CAMERA: One grounded third-person gameplay camera behind and slightly beside her at roughly waist height, over-the-shoulder offset, dropping lower during crouch. Smooth stick-driven tracking with slight lag, realistic collision with hutches and fences, no floating camera or unnecessary cuts. AUDIO: Natural farm ambience, birdsong, distant goats, wind in grass, boots on dirt and grass, rabbit hops and thumps, soft chewing, hutch wood creaking, the metallic jingle of the key, greens hitting the trough, subtle breathing, and faint rabbit sniffing. Light UI sounds only: soft chime on objective updates, quiet tick on button prompts, a gentle completion sting at the end. No dramatic action music. REALISM LOCK: Authentic rabbit behavior (freezing, ear rotation, thumping, hopping rhythm, grazing), believable timing, realistic physics, fur, and collisions, populated farm environment with varied background animal actions. Game-engine look with consistent lighting and materials. No teleporting, invisibility, supernatural stealth, parkour, talking or anthropomorphic animals, duplicated rabbits or characters, changing identity/outfit/key, impossible hiding, exaggerated acting, anime/cartoon style, filmic camera moves, subtitles, logos, or watermarks other than the described in-game HUD.
Details
0:10
Runway Gen-4
Create a hyper-realistic full-body fall street-style fashion portrait of a stunningly beautiful adult woman with refined, model-like features, balanced facial proportions, defined cheekbones, expressive light-colored eyes, full natural lips, and long, voluminous wavy blonde hair with darker dimensional roots. She is walking directly toward the camera with confident, effortless runway-like movement while maintaining direct eye contact with the lens. Dress her in a fitted black long-sleeve turtleneck mini dress with a clean minimalist silhouette, ending at the upper thigh. Pair the dress with semi-sheer black tights and sleek black leather lace-up ankle boots with a substantial but refined sole. Add a simple short gold chain necklace as the only prominent accessory. Keep the outfit sophisticated, monochromatic, unbranded, and appropriate for a stylish fall city setting. Place her on a busy upscale urban sidewalk during peak autumn, surrounded by mature street trees filled with dramatic deep-red, burgundy, rust, and crimson foliage. Fallen leaves are scattered naturally across the pavement. Storefronts and mid-rise city architecture line the street, with parked and moving cars along the curb. Several realistically dressed pedestrians move naturally through the background and edges of the frame, giving the scene authentic city energy without distracting from her. Capture her mid-stride, with one leg naturally crossing slightly ahead of the other. Her arms swing subtly and naturally with her movement, her shoulders remain relaxed, and her posture is upright and confident. Avoid an exaggerated runway pose. She should look like an exceptionally stylish woman genuinely caught walking through the city. Frame her completely from head to toe, with both boots fully visible and comfortable breathing room around her body. Shoot from approximately eye level using a 50mm full-frame lens, producing natural proportions and moderate environmental compression. Keep her sharply defined while allowing the pedestrians, cars, storefronts, and distant street to transition gradually into shallow cinematic depth of field. Use spectacular late-afternoon autumn cinematography with soft directional daylight filtering through the red foliage, subtle warm highlights along her hair, realistic shadow detail, controlled contrast, and rich but believable fall color. Give the photograph a sophisticated high-fashion street editorial meets candid 35mm photography aesthetic rather than a polished studio or artificial AI-fashion appearance. Hyper-realistic photography, stunning model-like beauty, authentic skin pores and micro-texture, natural complexion variation, realistic eyes, individual eyelashes, individual hair strands, detailed blonde hair highlights, realistic fabric texture, natural garment folds, physically accurate hands and fingers, anatomically correct legs and feet, realistic pedestrian faces and bodies, authentic autumn foliage, subtle film grain, beautiful highlight roll-off, high dynamic range, cinematic depth of field, premium photographic detail, no fake skin, no plastic skin, no waxy complexion, no excessive smoothing, no CGI appearance, no animated look, no distorted anatomy, no warped hands, no artificial-looking background people, no image degradation.
Details

About Runway Gen-4

Runway Gen-4 is the generation model from Runway, a company that has spent years building AI tools specifically for filmmakers and video professionals. It produces both images and video, and its defining idea is reference-driven generation: you give it images of a character, a location, or an object, and it keeps them recognizable across new shots.

That makes its core strength continuity — the thing that has separated AI clips from actual filmmaking. Where most models reinvent your protagonist every generation, Gen-4 holds a character's identity steady across angles, lighting setups, and scenes, letting you build a consistent world rather than a pile of disconnected shots. For storyboards, short films, and episodic content, that changes what is possible.

Working this way is a different craft: the reference carries the look, and the prompt directs the scene. The gallery below collects tested Gen-4 prompts with their real outputs, so you can study how working prompts split those responsibilities before shooting your own sequence.

How to write Runway Gen-4 prompts

  1. 1Start from references, not adjectives. Give Gen-4 clear images of your character or location, then keep those references fixed across every shot in the sequence — that is where the consistency comes from.
  2. 2When a reference carries the look, spend the prompt on direction instead: describe the action, the emotion, and the camera, not the character's appearance the reference already establishes.
  3. 3Name one camera move per shot — "slow push-in on her face", "handheld follow through the market", "static wide as the storm rolls in". One instruction keeps the motion readable.
  4. 4Write a mini world bible and reuse its exact phrases: the same character name, the same location wording, the same lighting description across prompts reinforces continuity between shots.
  5. 5Keep each generation to a single story beat. Chain several short shots into a sequence instead of cramming a scene's worth of events into one prompt.
  6. 6Carry the grade across cuts with a repeated mood clause — "overcast steel-blue light, muted grade" — so consecutive shots feel like they belong to the same film.

Frequently asked questions

What is Runway Gen-4 best at?

Continuity. It keeps characters, locations, and objects consistent across shots, which makes it a strong choice for filmmakers building sequences — storyboards, short films, music videos — rather than isolated clips.

How does Gen-4 keep characters consistent across shots?

Through reference images. You provide visuals of your character or world, and Gen-4 preserves their identity in new angles, lighting, and scenes. Fix the references for a whole sequence and let the text prompt vary the action and camera.

Can Runway Gen-4 generate images as well as video?

Yes — Gen-4 covers both. A common filmmaker workflow is to explore a scene as still frames first, pick the frame that works, then move to video with the same references and prompt language to keep the world intact.

Where can I try these Runway Gen-4 prompts?

Gen-4 is available in Runway's web platform, alongside the rest of its filmmaking toolset. Copy a prompt from this page, bring your own character or location references, and adapt the camera and action language to your scene.

Related models

GPT Image 2

OpenAI's top-ranked image model — it plans the layout, reasons, and self-checks before it draws, nailing complex multi-part instructions.

image
273 prompts

Seedance 2.5

Seedance 2.5 is a next-gen AI video model that generates continuous, synchronized 30-second 4K clips from a single prompt.

video
262 prompts

MiniMax H3

MiniMax H3 is a powerful multimodal video generation model that creates up to 15-second 2K videos with native stereo sound from text, image, video, and audio inputs.

video
203 prompts

GPT Image 2.5

OpenAI's GPT Image 2.5 — up to 50% faster than Images 2, with pinpoint local edits that leave the rest of the frame untouched and reference subjects that stay recognizable across repeated rounds.

image
181 prompts
Browse AI Image PromptsBrowse AI Video PromptsAll models