NewOpenClips MCP is live.Your AI video studio, inside any AI chat.See how it works →
Pricing
Luxury fragrance commercial rendered as a finished AI ad
mcp.openclips.ai

● REC · Your idea starts here

AI video generator. Your ideas, in motion

Turn a prompt or image into a video worth sharing. Start with your idea, or build on a community workflow.

GeneralSeedance 2.5

Free to brief. 50 credits on signup. No card.

Seedance Omni Flash MiniMax Hailuo Kling Happy Horse Grok Imagine Veo Runway Seedream Nano Banana GPT Image Ideogram Recraft Wan Z-Image Luma Ray Flux Pika Imagen SDXL Seedance Omni Flash MiniMax Hailuo Kling Happy Horse Grok Imagine Veo Runway Seedream Nano Banana GPT Image Ideogram Recraft Wan Z-Image Luma Ray Flux Pika Imagen SDXL

Pick your use case

What are you launching?

Four buyers, four shelves. Every card is a real format with a real price behind it.

Ad formats

AI video ad generator for commercials that ship.

You stop briefing an agency for every cut. Pick an ad format. The price is on the card before you render.

TV Commercial

10s / 15s / 20s / 30s

Cinematic

10s / 15s / 20s / 30s

Product spec

10s

Creator-style

Paste a product URL. Get UGC ads.

You stop booking creators. Pick a format. The price is on the button.

UGC ad

15s / 30s / 40s

POV

15s

Street interview

15s / 30s

Ecommerce ads

Ecommerce ads for every SKU and every sale.

Unboxings, product shots and before-and-afters, plus the image ads around them. One product photo in, a launch set out.

Unboxing

15s

Product shot

15s

Before / after

15s

Listings

Make real estate videos from listing photos.

You stop hiring a crew for every listing. Pick a shape. The price is on the card.

Property ad

30s

UGC tour

30s

Cinematic film

30s

See what the world is rendering

AI videos the community rendered. Prompts included.

Real clips, real prompts, the model that made them. Remix any with one click.

Enter the community
Inspired by @ou_zhen599on X

UNDERGROUND TEMPLE. ONE EXPLORER. FIFTEEN SECONDS. 16:9. ASSET MAP - every reference is bound here and cited by tag below: @avatar_1 - the explorer, and the only person in the film. Face, hair, hair length, hair colour, skin, age, build and every physical characteristic come entirely from @avatar_1 and never from this text. IDENTITY LOCK - HIGHEST PRIORITY: the explorer is exactly the person in @avatar_1 and stays exactly that person in every shot. Do not restyle the face, do not change the hair colour or length, do not age them up or down, do not slim or reshape the body, and never swap in a different person. ONE BODY ONLY - COUNT THEM: exactly one human being exists in this film. There is never a second figure, never a companion, never a double, never a reflection or silhouette of another person, and never a second body in the foreground of a shot. Any shoulder, arm, hand or back of a head that appears in frame belongs to @avatar_1 and to nobody else. If a framing would normally need a second person to stand in front of the camera, do not use that framing. ATTACHED REFERENCES ARE MANDATORY AND FINAL: if a reference is attached, that is the explorer - reproduce them exactly, in every shot, and never invent a different one. The attached reference outranks every word written below it. WARDROBE LOCK: a plain dark sleeveless top, fingerless leather gloves worn to the knuckle, a wide belt with small pouches, cargo trousers tucked into worn lace-up boots. No jewellery, no badges, no lettering and no logo anywhere on the clothing. This list is clothing only and says nothing about hair. THE HAIR COMES FROM THE REFERENCE, NOT FROM THIS TEXT: whatever hair @avatar_1 has is the hair in the film - the same length, the same colour, the same texture, from the first frame to the last. If it is short it stays short, if it is long it stays long, if it is tied up it stays tied up, if there is none there is none. Never add length, never add a ponytail or loose strands that the reference does not have, never restyle it to suit the scene, and never let dust, movement or the action change what kind of hair it is. THE PLACE: a buried stone temple, long abandoned. Carved pillars and low arches, walls cut with deep interlocking relief, roots and pale green creeper coming through the joints, standing water in the dips of a cracked flagstone floor, drifting dust. The only light is a scatter of stubby candles burning low on the stones, plus one narrow shaft of daylight from far above. Warm candle flame against cold blue shadow, everything else near-black. THE LOOK: photographic and close, shot on a fast prime wide open - very shallow focus, strong bokeh on the candle flames, handheld with a live but controlled wobble, fine grain, no gloss. Warm amber on skin, deep blue-green in the dark. THE CUTTING: exactly five shots, hard cuts between them, with the lengths given below. Each shot is its own framing - never let two of them run together as one continuous move. THE CARVING: one panel of the wall is cut with a dense spiral pattern. When a hand touches it, thin lines of warm light run along the grooves and spread outward from the touch, then fade. The light is inside the carved lines only - it never becomes a glow in the air, a hologram or a magical effect. Shot 1 (2.8s) Medium-wide, and @avatar_1 is the subject of this shot from the very first frame - already large in the picture, not a distant figure in the depth. @avatar_1 steps out of the dark between two pillars into the shaft of daylight, one hand trailing the wall, and stops. A few candles sit low at the edge of frame, well out of focus and never filling the foreground. The camera holds handheld. Shot 2 (2.6s) Medium close, from behind and slightly to one side of @avatar_1, the camera just past their own shoulder and nobody else in the frame. @avatar_1 leans in toward the carved panel, face lit from the side by candlelight, and reads the pattern with the eyes before touching anything. The camera drifts in slowly. Shot 3 (2.4s) HARD CUT to a macro insert, a separate shot of its own: nothing but the hand and the stone, framed so tight that no face and no shoulder are anywhere in the picture. The fingers settle into the carved spiral and thin lines of warm light run out along the grooves from under the fingertips. This must not be a continuation of the previous shot - it is a clean cut to a new, much closer framing. Shot 4 (2.6s) Close on the face of @avatar_1, lit now from the wall itself, the expression turning from concentration to understanding to alarm in one continuous take. The eyes go to something off to the side. The camera holds on the face. Shot 5 (4.5s) Wide, pulling back. @avatar_1 straightens up fast and steps away from the wall as the lines of light in the carving keep spreading past the panel and out across the stones of the whole chamber, running along the joints toward the camera. @avatar_1 backs out of frame and the temple is left lit by its own lines. Hold to the last frame. DIALOGUE: @avatar_1 speaks twice, quietly and to themselves, and these are the only words in the film: In Shot 2, half under the breath: <Someone got here first.> In Shot 4, barely voiced, as the understanding lands: <That's not a trail.> SOUND: a deep buried-room tone with a long slow reverb. Water dripping into a pool somewhere off to the side, grit under a boot, the small dry crackle of candle flames, cloth and leather as they move, one slow breath before the first line. Under all of it a low sustained bass note that sits quietly through the first four shots and then swells and opens out as the light spreads in the final shot - the only moment the score makes itself felt. Do not generate subtitles, captions, on-screen text, a title card, a logo, a wordmark, a watermark or any readable lettering or numerals anywhere in frame. The two spoken lines are heard, never written on screen. No second person, no torch, no flashlight, no modern equipment, no magical glow in the air, and no change to the explorer's face, hair or build at any point.

2 steps3161
Seedance 2.515s · 1:1
Inspired by @tlakomyon X

VINTAGE GRAND PRIX. THREE DRIVERS. NO DIALOGUE. THIRTY SECONDS. 21:9. ASSET MAP - every reference is bound here and cited by tag below: @avatar_1 - the driver of car number 1. Face, hair, skin, age, build and every physical characteristic come entirely from @avatar_1 and never from this text. @avatar_2 - the driver of car number 2. Face, hair, skin, age, build and every physical characteristic come entirely from @avatar_2 and never from this text. @avatar_3 - the driver of car number 3. Face, hair, skin, age, build and every physical characteristic come entirely from @avatar_3 and never from this text. IDENTITY LOCK - HIGHEST PRIORITY: each driver is exactly the person in their own reference. Keep their face, hair, skin tone and build the same from the first frame to the last. Do not restyle them, do not age them up or down, do not slim or bulk the build, never swap which reference drives which car, and never put a fourth driver on the track. Three drivers, the same three, for the whole film. ATTACHED REFERENCES ARE MANDATORY AND FINAL: if a reference is attached, that is the driver - reproduce them exactly, in every shot, and never invent a different one. The attached references outrank every word written below them. CAR AND DRIVER PAIRING - NEVER BREAK IT: @avatar_1 drives the red car with a white roundel and the numeral 1. @avatar_2 drives the dark green car with a white roundel and the numeral 2. @avatar_3 drives the pale blue car with a white roundel and the numeral 3. The numerals on the cars are the only numbers allowed anywhere in the film. WARDROBE LOCK: all three wear the same cut of plain period racing kit - a light canvas one-piece with a wide leather belt, a soft leather helmet and round goggles pushed up on the forehead, and leather gauntlets. The kit differs only in colour, matching each driver's own car. No lettering, no sponsor patches, no badges and no logos anywhere on the kit or the cars. THE CARS: three small open-wheel single-seaters from the late nineteen-fifties - riveted aluminium bodies, exposed suspension arms, tall thin tyres with visible spokes, a single mirror on a stalk, no wings and no modern aerodynamics. They sit low and look hand-built. THE PLACE: an old countryside road circuit at the last hour of daylight. Cracked tarmac, painted red-and-white kerbs, hay bales and low wooden fencing, mown grass banks, a long avenue of trees down one side, a wooden footbridge over the track, a small empty timing tower and a shallow grandstand of bare wooden benches. THE LOOK: shot on film at golden hour and graded warm - long low sun straight down the track, heavy lens flare, dust and pollen lit in the air, shallow depth of field, gentle anamorphic stretch on the highlights, fine grain. Everything is amber, brass and deep green. The sun is always low and always in shot or just outside it. THE CUTTING: exactly seven shots and no more. Each one is long and unhurried and runs its full length without an internal cut. Do not break any shot below into several shorter ones - the camera does the work, not the edit. Shot 1 (5.6s) Wide, low and head-on. The three cars sit side by side on the grid, engines running, heat shimmering off the bonnets, the low sun directly behind them throwing long shadows toward camera. @avatar_1, @avatar_2 and @avatar_3 sit in their cars looking ahead. The camera pushes in slowly. Shot 2 (4.2s) High and wide, looking down on the circuit as the three cars come off the line together and take a long sweeping bend in formation, dust lifting off the kerbs behind them. The camera drifts with them. Shot 3 (5.2s) Low, on the tarmac under the wooden footbridge, looking up the track. A single carrot lies on the racing line right in the foreground, very close to the lens and filling a good part of the bottom of frame, sharp while the track behind it is soft. The three cars come through the bridge's shadow at speed and burst past it, and the carrot is torn apart into a spray of orange fragments across the road. The camera holds low as they pass over. Shot 4 (5.0s) ONE UNBROKEN SHOT, no cut inside it: in the car with @avatar_1, camera mounted just ahead of the cockpit and locked on the face for the full five seconds. Goggles down, jaw set, the whole frame shaking with the road, hedges and trees tearing past in a blur, dust and low sun flaring across the lens. This is the fastest and roughest shot in the film and it must run as a single continuous take. Shot 5 (4.2s) Wide and almost still. The long straight with the sun sitting exactly on the road at the end of it. The three cars are small black silhouettes running dead into the light, their shadows stretched enormous behind them. Almost nothing moves in frame but them. The camera holds. Shot 6 (2.2s) Track level at the grandstand. The cars come past flat out, close to camera, and a marshal standing at the trackside edge of frame waves a small chequered flag on a short wooden pole as they cross the line. The flag is a real cloth flag held in a hand, moving with the wave - it is never a band, strip or banner stretched across the top or bottom of the picture, and never an overlay on the image. Shot 7 (3.7s) The podium at sunset. A real three-step wooden podium stands beside the track with three clearly different heights - a tall centre step, a lower step to its left, a lower step again to its right. @avatar_1 stands on the tall centre step and is visibly higher than the other two. @avatar_2 stands on the left step and @avatar_3 on the right step, both lower. Each of them does something different: one raises both arms, one folds their arms and grins, one is still pulling their goggles off. Do not give the three of them the same pose or the same gesture. Goggles pushed up, dusty and pleased, the last of the sun going down over the trees behind. The camera pushes in slowly and holds to the final frame. MUSIC - THIS FILM IS SCORED AND THE SCORE IS LOUD AND PRESENT, WELL IN FRONT OF THE ENGINES. A warm orchestral score with brass and strings, the sound of an old sports newsreel, and it is tied to three things that happen on screen: It sits low and tense, strings only, while the cars are standing still on the grid. On the exact frame the three cars move off the line, a rising brass note lifts and the full theme starts running, driving and bright, and carries the whole chase. On the exact frame the chequered flag is waved, one big brass swell lands at once, at least twice as loud as anything before it, and then opens out warm and broad over the podium and holds to the final second. Mix the music loud - it should be the first thing anyone hears, and it must be clearly louder at the end than at the start. The engines are always quieter than the music. At every moment of the film the score sits on top and the engines sit underneath it, and the gap between them widens toward the end: over the podium the music is at its loudest of the whole film and the engines have stopped altogether. ENGINE AND ROOM SOUND, KEPT WELL BELOW THE MUSIC AT ALL TIMES: three small unsilenced engines at different pitches, gear changes, tyres over kerbs, gravel flicking up, wind and a flag snapping. These are background texture only - they must never be as loud as the score, never mask it, and they fade out completely on the podium so the last six seconds are music alone. No voices, no commentary, no dialogue, no lyrics, no singing. Do not generate subtitles, captions, on-screen text, a title card, a sponsor board, a brand name, a logo, a wordmark, a watermark or any readable lettering anywhere in frame. The only numbers allowed are the 1, 2 and 3 on the cars. No modern cars, no modern clothing, no rabbits or animals of any kind, no fourth driver, and no change to any driver's face or build at any point.

4 steps5251
Seedance 2.530s · 1:1
Inspired by @aimikodaon X

Use @image1 for the character's identity, anatomy, costume, colors, materials and visual style. Adapt body-region cues to their actual anatomy, replacing absent features with existing equivalents. Invent no anatomy or accessories. Select signature inserts from their most recognizable details. Rigid parts rotate; flexible materials bend or stretch. Hyperrealistic macro photography throughout: every insert reads as a real lens held close to a real surface, with visible weave and thread, leather grain, brushed and scratched metal, dust caught in the light, shallow macro depth of field falling off softly, physically accurate light and true material response. No illustration, no cel shading, no painterly or hand-drawn rendering, no comic or animated look, no plastic CGI sheen, no smooth airbrushed surfaces. A character-detail montage: exactly 20 shots joined by hard cuts. An empty, seamless warm-white studio background; soft directional light reveals the surfaces. Shots 1-19 are tightly cropped body details and rear angles: keep the face, eyes and facial profile entirely outside the frame, including reflections. Shot 20 is the first and only face reveal. No full-body view. Three connected bursts: a sharp head turn with the body bracing; a coiled arm opening into a strong sweep and torso twist; one short step into a planted pivot, finishing with a sudden look into camera. Carry body state across cuts without resetting to neutral. Existing hair, clothing and attachments react naturally. Keep the character active, with clear articulation and weight shifts. Jump between distant body regions. Mix brief visual punches with longer moving-detail reads. Use one abrupt camera move per shot except locked-camera inserts 4 and 11, where the character supplies the speed. Vary height, angle and direction. Brake moves briefly for legibility while the subject keeps moving. Local whips stay tightly cropped; changes of body region use hard cuts. Connect selected cuts through similar shapes or motion vectors, without morphing. Real-time action, no slow motion or freeze frames. Shots 1-5. A concealed head turn triggers the first burst: 1. Extreme upper-back detail: a crash push catches its surface shifting as a sharp head turn begins entirely above the crop. 2. Fingers: a short downward snap catches them curling into a fist as the body braces. 3. Rear three-quarter shoulder detail: a tight camera arc catches the shoulder drawing back behind the turning head. 4. Locked floor-level foot detail: the grounded support foot braces, its raised heel pressing down firmly without taking a step. 5. Rear neck detail: a short upward tilt catches the nape stretching with the turn; stop below the back of the head, keeping the jaw and face excluded. Shots 6-13. The coiled arm opens into a forceful sweep: 6. A signature upper-body detail: a fast diagonal slide catches an existing seam, joint or distinctive contour responding as the arm draws inward. 7. Elbow: a sharp lateral track catches the folding joint tightening the arm's coil. 8. Supporting knee: hard match cut from the bent elbow to the knee's similar angle; a short camera drop catches the leg compressing under the same preparation. 9. Wrist: a quick shallow orbit catches it turning outward to initiate the release. 10. Upper chest: a short punch-in catches the chest opening as the arm drives outward beyond the crop. Let this moving surface read slightly longer. 11. Locked hand detail: fingers spring open and the hand sweeps rapidly across the fixed frame. Catch one crisp, readable phase of the spread fingers before they leave the crop. 12. Upper back: a sharp sideways slide continues that screen direction as the shoulder rolls through the sweep and the torso twists. 13. A distinctive torso or waist detail: a close diagonal move catches its physical response to the twist, such as an existing fold pulling taut or an attached piece swinging. Give the material response a clear moving read. Shots 14-19. One short step and a pivot build toward the reveal: 14. Thigh of the other leg: an abrupt low tracking move catches it driving the single short step out of the twist. 15. Advancing foot: a brief downward whip catches it landing; show clear floor contact. 16. Ankle and lower-leg detail: a fast side slide catches the landed leg accepting weight as the ankle flexes. 17. Waist: a tight orbit catches the torso rotating above the planted-foot pivot. The foot supports the turn rather than sliding across the floor. 18. Back-of-head contour: a short lateral whip catches the start of the return turn from behind. Keep only the rear contour in frame, never the facial profile. 19. A signature shoulder detail: a sharp diagonal slide catches its follow-through beneath the turning head, which stays completely above the crop. Cut at the peak of this movement. Shot 20. First face reveal: 20. Hard cut to a frontal face close-up as the character sharply completes the turn toward the lens. An explosive short push reveals the entire face clearly for the first time and stops tightening before cropping out their features. Direct eye contact lands while hair, clothing or natural body follow-through remains alive. Keep the whole face readable through the end; finish on living motion, without a held pose or another cut. No added props, scenery, text, graphic overlays or split screens.

3 steps044
MiniMax H315s · 16:9
Inspired by Naiknelofar788on X

Create a 15-second ultra-realistic cinematic 16:9 video. Sound ON. If Montenegro were a chocolate bar. ATTACHED IMAGES ARE THE COUNTRY — photocopy them, do not invent a generic coast or Alps. @image1 is the REAL Sveti Stefan: tiny Adriatic island packed with stone houses and terracotta roofs, connected by a narrow causeway/isthmus, turquoise water, pink-orange stone. @image2 is the REAL Durmitor: high pale-grey limestone peaks, jagged, alpine, sparse snow, not rolling green hills. OPENING: dark chocolate bar, red-gold wrapper, dark table. Hand snaps it. The break REVEALS these two places, unmistakably: first Sveti Stefan as in @image1 (island + isthmus + packed roofs), then Durmitor as in @image2 (high karst massif). Melted chocolate = bay. Crumbs = karst. Finish aerial: Sveti Stefan in water in front, Durmitor peaks behind. Broken chocolate at edges. No Japan, no Fuji, no generic Cinque Terre, no on-screen text. AUDIO: snap, sea, mountain wind. No vocals. Duration 15s. Aspect 16:9.

1 step
Seedance 2.515s · 16:9
Inspired by BerryBattyToyson X

A 12-second photoreal cinematic 16:9. No on-screen text, no logos, no people. @image1 is the T-rex: pink-cream body, red-pink head spines, ivory snout, leaping through sunset peach clouds. Keep that exact creature until the morph. AUDIO: wind, dinosaur run, then wingbeats. No dialogue. [0-6s] Fully a T-rex the whole time. Runs and leaps through sunset cumulus. Tiny forelimbs, massive tail, scales. Camera tracks. NO feathers yet. NO beak yet. [6-9s] NATURAL morph over these three seconds only — not a snap, not a dissolve to a different animal: second 6: small feathers push through the scales along the back and arms; skin-sails start at the shoulders; second 7: wings lengthen, plumage fills in, the snout shortens and the jaw reshapes into a curved beak — same head turning into a macaw beak, not a cut; second 8-9: macaw colours (red, blue, yellow, green) finish across the body; wings spread. Same creature, same leap, continuous. [9-12s] Full macaw. Flaps and flies through the same peach clouds. End. NEGATIVE: a pop-cut at 3 seconds, a different animal appearing, extra creatures, text, remaining a T-rex after 9s, studio still as frame 1.

1 step430
Seedance 2.512s · 16:9
Inspired by @SyntheSarahon X

【Generation Goal】 Generate a premium cinematic short film in which someone only a few inches tall crosses a worktable, finds a tear in an enormous jacket, threads a needle taller than they are, repairs the seam by hand, and is finally revealed riding in the breast pocket of the finished jacket as a giant wears it. 【Visual Style】 High-end cinematic 3D animation of polished feature-film quality, with realistic materials, detailed fabric, natural textures, physically based lighting, realistic shadows and subtle depth of field. Cloth reads as real wool and cotton with legible weave, fibre and thread detail and correct weight in every fold. Cloth, wood, metal and paper each read as their own material. Skin is soft and matte with subsurface warmth. Long soft shadows and rich material separation, with the lighting taken from @image2. Do not render a plastic, vinyl, toy or figurine look, cartoon physics, clay or stop-motion surfaces, photoreal live-action photography, ink outlines or line-art contours, cel shading, flat banded shadows, comic, manga, anime or webtoon styling, or vector or flat-illustration fills. 【Reference Asset Roles】 @image1 defines the character's face, hair, body proportions, clothing and accessories; take the identity and costume entirely from it and do not adopt its neutral background. @image2 defines the location and every object in it: the workshop, the worktable, the jacket, the needle, the spool of thread, the measuring tape, the tools and the lighting. It also defines scale — the size relationship between the character and every object is fixed by @image2 and never changes. Do not take any person from it. @image3 is the storyboard and governs shot order, framing, staging, character position and camera geography; read it left to right and then top to bottom, and do not adopt its panel grid, gutters or flat layout into the video. 【Subjects and Relationships】 There is one continuous character throughout, defined by @image1, only a few inches tall. Use they / their / them. They are never swapped, duplicated, replaced or altered in face, hair, clothing, proportions, colours or accessories in any shot. They work with calm, practised care and quiet pride. A second, giant person appears late — first as a hand and wrist entering frame, then as a body wearing the jacket. This giant is always framed so that no face and no head is visible: the hand shot shows only hand and wrist, and the final shot is framed from the chest down. The giant is never described, never turns toward camera and never speaks. The jacket, the needle, the spool of thread, the measuring tape and the worktable stay consistent in size, shape, position and appearance throughout. The tear exists until it is stitched, and once stitched it stays closed. 【Event Script】 Stage 1: A wide low shot along the surface of the worktable. The character walks steadily across the table toward the jacket spread out ahead of them, the coiled measuring tape carried over one shoulder. At the end, they are partway across the table and the jacket fills the ground ahead. Stage 2: They reach the edge of the jacket and stop at the foot of the fabric, tipping their head back to look up as the lapel rises above them. At the end, they are standing still at the base of the cloth, looking up. Stage 3: They climb onto the wool and cross to the failed seam, then crouch beside the open tear and lay a hand on the frayed edge, tracing its length. At the end, they are crouched at the tear with the split clearly open in front of them. Stage 4: They cross to the needle lying on the table and stand at its eye, raising the end of the thread with both arms and feeding it through the open loop. At the end, the thread is through the eye and they hold the doubled end. Stage 5: They set the needle into the wool and haul it through, braced back against the weight, the thread drawing after it in a long line. The cloth dimples and releases around each pass. At the end, the first stitches are laid and the needle is clear of the fabric again. Stage 6: A closer frame travels along the seam as the work continues, the tear closing behind a run of neat even stitches. They kneel at the last stitch and draw it tight. At the end, the tear is fully closed and the seam is clean. Stage 7: They step back onto the jacket, hands on hips, and look along the finished seam. An enormous hand descends into frame, closes on the cloth and lifts it, and they ride the rising fabric, catching their balance. At the end, the jacket is off the table and they are holding on. Stage 8: The camera pulls smoothly and steadily back into a wide shot. A giant stands wearing the repaired jacket, framed from the chest down. The character sits in the breast pocket with the needle held upright beside them, looking out. The shot holds on that final state. Throughout, movement is unhurried and physically believable, with correct anatomy and natural human-like motion. Objects have real weight — the needle is heavy, the cloth resists and settles, the thread has slack. Dust turns slowly in the raking light. Camera moves are smooth and cinematic with stable framing and consistent perspective; there are no rapid cuts, no camera jumps, no morphing, warping or artifacts, and no impossible physics. 【Sound】 <the soft scuff of small footsteps on polished wood>, <cloth shifting and settling under weight>, <the fine rasp of thread drawn through wool>, <a single quiet tap as the needle is set down>, <a distant clock in another room>, <the low hum of a warm afternoon workshop>. No one speaks, no narration, no music, and no subtitles appear on screen. The character keeps their mouth naturally closed throughout. 【Maintain Consistency】 Keep the character's identity, face, hair, clothing, proportions, colours and accessories exactly as defined by @image1 in every shot, with no drift or reinterpretation. Keep the workshop, worktable, jacket, needle, thread, measuring tape and lighting consistent with @image2, and hold the scale relationship between the character and every object fixed throughout. Keep the giant's face and head out of frame in every shot they appear in. Keep the tear closed once it is stitched. Keep the shot order, framing and camera geography matching @image3. Do not generate any text, titles, captions, subtitles, logos or watermarks.

5 steps957.4K
Seedance 2.530s · 16:9
Inspired by @Dyyaiworkeron X

22 seconds, 16:9, eight shots, no speech. @image_1 and @image_2 are the two riders and the only attached assets. ATTACHED IMAGES ARE MANDATORY AND FINAL: @image_1 and @image_2 decide who these two people are; where this text and an attached image disagree, the attached image wins. Never draw one rider with the other's face and never swap them between shots. CHARACTER LOCK: the whole film is drawn in the animation style below, and inside that style each rider is unmistakably the person in their own attached asset - same face shape and features, same hair colour, length and texture, same skin tone, same build, same apparent age. Stylised, never re-cast. Preserve the gender presentation of each rider exactly as shown. Every hand in frame has five fingers. HEADS ARE BARE - THIS IS THE POINT: both riders ride bare-headed in every shot, the whole face uncovered and readable, hair loose and streaming in the airflow. WARDROBE LOCK: @image_1 in a fitted forest-green riding suit with cream shoulder panels, @image_2 in a fitted cream suit with rust-orange shoulder panels; both with tan leather slide gloves and dark knee pads. Each suit is fixed, only its drape adapts to that rider. STYLE: a stylised animated short. Solid three-dimensional forms lit by one low sun, with painted surfacing laid over them - matte, warm, simplified. Low autumn light rakes between the trunks and strobes across the riders. Longboard physics are real: gravity, inertia, grip and weight transfer. THE PLACE: a single-lane road winding down a wooded hillside. Birch, beech and maple in gold, amber, rust and deep red, the canopy closing overhead into a tunnel of colour, drifts of fallen leaves along the verges, mossy boulders, a low wooden guardrail and mist in the hollows. Low down the hill the road itself crosses a shallow stream on a small stone bridge: the bridge carries the road, a low stone parapet runs along each side, and the riders ride over it. Everywhere else the road sits on solid ground for its whole width, with verge and forest floor visible along both edges, so it always rests on the hillside and is never lifted above it. [0-3s] Already at full speed - nothing starts from rest. Low camera near the tarmac, tracking behind and to the side; both tucked but heads up and faces visible. [3-5s] The camera drops in front and tracks backwards low to the road. Both faces full to camera, @image_2 half a board ahead, @image_1 tight in the slipstream. [5-8s] First fast corner: @image_2 runs wide, @image_1 takes the inside line, both leaning together, leaves torn off the verge. [8-11s] Whip pan through the trunks, gold smearing across frame, then both burst back into shot lower down the hill. [11-14s] Close on @image_1, front three-quarter, the whole face in frame, hair whipping. [14-17s] A leaf-covered hairpin: both drop a gloved hand and carry a long powerslide, dry leaves exploding off the tarmac. [17-20s] @image_1 pulls out of the slipstream and draws level, then ahead; the two glance across at each other and half-smile, both faces in the same frame. [20-22s] Wide and high from behind: the road runs away into a tunnel of gold and in the middle distance carries the two riders over the little stone bridge, its low parapet passing on either side. They are small and side by side, shrinking into the light. AUDIO: driving instrumental music across the whole cut; under it wheels on tarmac, rush of air, leaves skittering, the scrape of a glove puck in the slide, birds at the end. There is no speech anywhere in this film. The eight shots run back to back with no gaps; the first frame is already moving at speed. No subtitles.

3 steps19145
Seedance 2.522s · 1:1
Inspired by AIwithSynthiaon X

Generate a UGC video, reviewing the product you want.

3 steps12613.1K
Seedance 2.515s · 9:16

Every AI video model. One login.

56 live AI models. One login.

Draft on a fast model. Finish on the flagship. Every render lands in one library.

Seedance 2.5FLAGSHIP

ByteDance · video · The flagship. Full scenes in one take.

from ⚡41

Seedance 2.0

ByteDance · video · Native 4K and strong prompt adherence.

from ⚡17

Gemini Omni FlashFLAGSHIP

Google · video · Google any-to-any video with built-in sound.

from ⚡17

MiniMax H3

MiniMax · video · Nine reference stills in one brief, out at 2K.

from ⚡39

Hailuo 2.3

MiniMax · video · Two fixed stops, and you know both prices.

from ⚡100

Kling 3.0HOT

Kuaishou · video · The image-to-video workhorse creators favor.

from ⚡46

Happy Horse 1.1NEW

Happy Horse · video · The newcomer built for character-consistent story clips.

from ⚡86

Grok Imagine 1.5FLAGSHIP

xAI · video · Rapid generation with bold aesthetics.

from ⚡19

Coming soon

Announced, not running yet. Each page names the live model that does the job today.

OpenClips MCP

Generate from your AI tool

Connect once. Then ask in plain words. Every live model answers, and the take lands in your library.

Server addresshttps://mcp.openclips.ai
ClaudeClaude CodeChatGPTCursorVS CodeGrokHermes agentOpenClawOther MCP client
  1. Step 01

    Connect your AI tool

    Claude, ChatGPT, Cursor, VS Code. One address, no API keys.

  2. Step 02

    Describe the clip

    Your agent picks the model and writes the shot. The ⚡ quote rides along.

  3. Step 03

    The take lands in your library

    Download it, remix it, or ship it. Credits settle automatically.

Pricing

Pricing that starts at free

One credit wallet across every model. The full rate card lives on the pricing page — after sign-in, the exact price of your render is on the Generate button.

Free

$0/mo

⚡50 on signup. No card required.

Try the image models. No card, no trial clock.

Start free

Starter

$9/mo

900 credits monthly

monthly only · cancel anytime

Choose Starter

Creator

$23/mo

3,200 credits monthly

billed $276/yr — save $72

Choose Creator

Pro

$63/mo

9,000 credits monthly

billed $756/yr — save $192

Choose Pro
Most popular

Studio

$149/mo

24,000 credits monthly

billed $1,788/yr — save $600

Choose Studio

Or top up once: $10/800⚡, no subscription.

See full pricing →
Share OpenClips
Your link carries a ?ref code. Signups through it are attributed to you.

Before your first clip

AI video questions, answered.

An AI video generator turns a text prompt, an image, or an existing clip into a new video. You describe what you want, choose a model, and the model renders it. OpenClips puts the major video and image models behind one composer, so the same idea can run on any of them.

Yes. Every clip in the community gallery shows the prompt behind it, and one click loads that prompt into the composer. The ready-made formats work the same way: pick the shape you need and the composer opens filled in, waiting for your product and your words.

Yes. Choose an image-to-video model, add your image, and describe the movement you want. Your selected model determines the supported inputs and settings. Use an image you have permission to use.

You can explore examples and prepare your idea for free. New accounts receive a one-time ⚡50 grant for selected starter image models. Video generation requires paid credits from a plan or credit pack. No card is required to create an account.

The credit cost depends on the model and settings you choose. After sign-in, the Generate button shows the quoted credit price before you confirm. Compare plans, credit packs, and the model rate card on the pricing page.

Choose a model or format that supports the shape your post needs. You can create a social clip, a product scene, or an ad, then review and download the result. Available aspect ratios depend on the selected model or format.

Length, resolution, and audio options depend on the model or format. The composer shows the settings available for your selection. Check those options before generating, especially when your project needs speech or sound.

No. You can buy a credit pack for an individual project or choose a plan for ongoing work. Credits are shared across the available models. Check the pricing page for billing details and the terms that apply to your purchase.

The flagships you can run today: Seedance 2.5, Kling 3.0, Veo 3.1, Grok Imagine 1.5, Hailuo 2.3, Wan 3.0, FLUX 3, Runway Gen-4.5, Happy Horse 1.1, Gemini Omni Flash, MiniMax H3 on video, and Nano Banana, Ideogram 4.0, Recraft V4.1, Seedream 5.0 Pro, Z-Image Turbo, GPT Image 2 on image. Every older version of each family keeps its own page on the models hub. Pika, Luma Ray, Imagen and SDXL are announced as coming soon. Sora 2 was discontinued by OpenAI, and its page shows what replaces it. New models ship fast.

Still have a question? Talk to OpenClips

Your next clip starts here

Have an idea? Make it move.

Bring a prompt, a photo, or a little inspiration. Give your next idea its first frame.

Free to prepare your idea. Video generation uses paid credits.