AI Video Generator

Cyclops Emerges

Model

Prompt

# ANIMATION PROMPT — iPHONE UGC, CYCLOPS EMERGES FROM THE CAVE (15 s)

SCENE CONTEXT
Photorealistic found-footage clip, 15 seconds, filmed entirely on a phone by the main character holding it. The main character is walking in a cold, foggy conifer forest when they notice something at a distant cliff, films their own reaction, turns the camera to show the cliff, and a colossal one-eyed giant climbs out of the cave mouth and turns to look directly at the lens. Handheld, real, unstaged. Restrained horror — tension and dread, not spectacle.

FORMAT AND DEVICE
Shot on an iPhone 16 Pro, rear and front cameras, held in their right hand. Vertical 9:16 frame. Real UGC phone-video look: handheld motion with the natural micro-tremor and drift of a hand, slight rolling-shutter skew on fast pans, visible auto-exposure hunting when the bright fog fills frame, brief autofocus searching when they zoom, mild highlight clipping in the pale sky, digital noise rising in the darker forest areas, light sensor sharpening on edges, and moderate compression softness in the fog gradients. A faint early-digital-video quality on top — slightly muddy blacks, mild colour smearing in the greys, a touch of interlaced-feeling motion on the fastest pans — but never a heavy filter, never a retro gimmick, never film grain.

The phone itself must NEVER be visible in frame — no phone body, no hand holding a phone, no screen, no reflection of a phone, no selfie stick, no UI, no recording indicator, no timestamps, no app overlays, no on-screen buttons. The image is what the phone's lens sees, nothing else.

ACTIVE REFERENCES — STRICT HIERARCHY

<<<image_1>>> (main character reference): controls the MAIN CHARACTER'S complete identity. This is the only human character reference image. It controls the face, identity, age appearance, gender, body proportions, hairstyle, hair colour, clothing, accessories, and overall appearance.

If image_1 shows a female character:
Use the exact female identity, face structure, body proportions, hairstyle, clothing style, accessories, and all visible details from image_1.

If image_1 shows a male character:
Use the exact male identity, face structure, body proportions, hairstyle, hair colour, clothing style, accessories, and all visible details from image_1. Adapt any gender-specific clothing elements naturally into a male version while preserving the exact same outfit concept, colour palette, materials, silhouette, and style.

The character's gender, facial features, voice, body structure, and overall identity must always match image_1. Never change the person into another gender. Never replace the face. Never blend with another face.

If glasses are visible in image_1, the character wears the same glasses. If glasses are not visible in image_1, do not add glasses.

<<<image_2>>> (second character reference): controls the secondary character identity only if needed. Ignore clothing, hairstyle, environment, and lighting from this reference unless explicitly stated. Do not blend this face with image_1. Image_1 remains the main character identity.

<<<image_3>>> (location plate): controls the environment 100% — the fogged spruce forest, the grey limestone cliff, and the enormous dark cave arch set into it. Same trees, same rock, same fog, same cold overcast palette.

<<<image_4>>> (creature sheet): controls the giant's anatomy, proportions, and scale 100% — including the human figure shown beside it for scale. Body build, head shape, single central eye, skin, hands, and stance all come from this reference.

Conflict rule:
Main character identity always comes from image_1.
Secondary character identity comes from image_2 only when required.
Creature always comes from image_4.
Environment always comes from image_3.
No blending of faces.

IDENTITY LOCK — <<<image_1>>> (100% match, zero drift)

The main character must be an exact identity match to image_1 in every frame.

Preserve:
- exact face shape
- eye shape and colour
- eyebrow shape
- nose structure
- lips and mouth shape
- jawline
- skin tone
- freckles, beauty marks, scars, and natural skin details if present
- hair style, hair colour, and length
- body proportions
- age appearance
- gender presentation
- clothing
- accessories

Do not beautify, stylize, age up, age down, or modify the person.

Real photographic skin texture only:
visible pores, natural skin variation, subtle imperfections, realistic texture, natural highlights and shadows. Never airbrushed, never plastic, never beauty-filtered.

The character must look like the exact person from image_1 captured by a real phone camera.

CYCLOPS SPEC AND SCALE LOCK (exact, non-negotiable)

Total standing height: 18.3 metres. Head 2.9 m crown to chin. Single eye 80 cm across, iris 45 cm, pupil 18 cm. Shoulder width 5.6 m. Arm span 19 m. Hand 3.1 m wrist to fingertip, palm 1.6 m wide, middle finger 1.4 m long. Torso 7.2 m shoulder to hip. Thigh 5.2 m, shin 4.6 m, foot 4.1 m long. A 1.75 m adult human reaches only just below its knee, exactly as shown beside it on the reference sheet.

Anatomy:
gaunt but hugely powerful humanoid, stooped forward, heavy rolled shoulders, deep ribbed chest, slack belly, long heavy arms hanging near the knees, thick columnar legs, bald elongated high-domed skull, one enormous eye centred in the forehead with no second eye and no socket where one would be, broad flattened nose, wide thin cracked mouth, large thin protruding ears, deeply wrinkled sagging skin, crude stitched hide loincloth.

Nothing added — no horns, no tusks, no armour, no hair beyond sparse stubble.

Cave relationship:
the cave arch is 24 m tall and 16 m wide. At 18.3 m the giant fits through it but not comfortably — he must duck his head noticeably and stoop to get out. This must be clearly readable.

LOCATION SPEC — <<<image_3>>>

A dense old-growth spruce and fir forest on a gently rising slope, thick cold fog filling the space between the trunks and thickening steadily with distance. Uneven forest floor of wet black earth, moss, low ferns, fallen mossy trunks, deadwood, and grey lichen-crusted stones.

Roughly 300 m ahead, a massive grey limestone cliff wall rises 220 m out of the fog, its face vertically water-streaked, bedded, fissured, and patched with pale grey-green lichen, with thin scrub and stunted trees rooted on ledges.

Set into it, the enormous cave mouth — a tall rounded arch of near-absolute blackness, 24 m tall, its edges hard and clean, its interior giving back no detail, with a band of mist drifting across its lower portion.

Mid-distance spruce tops cut across the arch's lower third so it is seen through and above the trees.

Only a narrow strip of flat pale grey-white overcast sky visible at the top of frame.

Cold, desaturated palette throughout — blue-grey, near-black, muted dark green, pale grey.

No sun, no directional shadows, no warm tones anywhere.

FOG SILHOUETTE LOCK — HOW THE CYCLOPS MUST READ (critical)

The fog between camera and cliff is DENSE. At 300 metres the giant must be almost dissolved by it. He is a silhouette and nothing more.

Tonal value:
his body sits only about one stop darker than the mist immediately behind him — a soft mid-to-dark grey shape against a slightly lighter grey wall of fog.

He must be clearly readable as a giant humanoid figure, but he must never separate from the fog as a solid, well-lit body.

What must NOT be visible on him at all:
skin texture, pores, wrinkles, folds, muscle definition, rib structure, veins, colour of any kind, the loincloth's detail, teeth, nostrils, ears, fingers as individual digits, or any surface shading that models his form.

No pale flesh tone.
No warm tone.
No highlights on his shoulders, chest, or thighs.

His whole body is one flat, almost featureless mass of grey.

Edges:
soft and eaten by the mist.

His outline is legible but never crisp — the fog erodes it continuously, and passing bands of denser mist partially swallow his legs, one shoulder, or an arm at different moments.

His feet and lower legs are almost entirely lost in the mist layer at the cave floor.

Where his silhouette overlaps the dark cave interior behind him, the two nearly merge and he is defined mainly by his upper edges against the paler rock.

Recognisable read:
despite all that, the silhouette must unmistakably say — huge stooped humanoid, bald domed head low between rolled shoulders, long heavy arms, one enormous hand gripping the rock edge, and the body barely fitting through the arch.

The eye:
the single exception.

His eye reads as a small, hard, pale near-white mark high and central on the head — a clean bright ring outline with a concentrated bright glint at its core, the only bright element anywhere on his body and the brightest small point in the frame.

It is the one detail the fog does not soften.

No glow spilling onto the surrounding skin, no light cast into the fog, no lens flare, no colour — just a pale white-grey eye-shape cutting through the grey silhouette.

When his head turns to camera, that mark swings around and locks onto the lens, sharpening slightly as it faces the light head-on.

Depth match:
his contrast, noise level, edge softness, and colour must match the limestone cliff beside him at the same distance exactly.

He is never sharper, never darker, never more detailed, and never more saturated than the rock around him.
CAMERA — EXACT

Handheld, phone in the main character's right hand.

Real hand motion throughout:
continuous small drift, low-frequency sway from breathing and body weight, and larger corrective movements when turning.

Never gimbal-smooth, never tripod-locked, never digitally stabilised.

The phone is never visible.

Beat A (front camera, selfie):
held at chest-to-chin height, about 40 cm from their face, angled slightly up so we see them from a fraction below eye level.

The lens is aimed back along the forest path, INTO the trees.

Beat B (rotation):
they physically swing the phone 180 degrees around to face away from them — a fast, messy, real rotation with heavy motion blur, rolling-shutter skew, and a brief exposure lurch as the bright fog enters frame.

Beat C (rear camera):
held at chest height, aimed forward and slightly up at the cliff, framing the forest gap with the cave arch in the upper-middle band.

They apply a slow pinch-zoom of about 2× on the cave, the frame magnifying in small stepped increments with a brief autofocus hunt as it settles.

Beat D (rotation back):
another fast 180-degree swing back to the front camera, same messy blur and exposure lurch.

Beat E (front camera):
held closer now, about 30 cm, less stable, drifting as they move their head and body.

Beat F (final rotation):
a third fast swing away from them, cutting the clip.

BEAT A FRAMING LOCK (0.0–2.6 s)

The cliff and the cave are NOT in this shot.

They are completely outside the frame, off to their right.

The main character is standing on the forest path with their back to the forest they just walked out of, and has turned their head to look off-frame to their right at the cliff — but that direction is not visible to the lens.

What is behind them in frame:
only the fogged spruce forest.

Dark wet trunks receding into grey mist, layered ranks of spruce and fir stepping progressively lighter with depth, the uneven mossy forest floor with fallen deadwood and low ferns, and a narrow strip of flat pale overcast sky through the canopy at the very top.

No cliff, no rock face, no cave arch, no limestone, no visible opening of any kind anywhere in this shot — not even partially, not even softened by fog at the frame edge.

The frame behind them is pure forest.

Their body is turned roughly 45 degrees away from the lens toward their right, and their head is turned further in that same direction — looking past the edge of the frame at something the camera cannot see.

Their eyeline clearly exits the frame to the right and slightly upward.

The viewer must understand from their eyeline alone that the thing they are looking at is off-screen.

ACTION TIMING

0.0–2.6 s — FRONT CAMERA.

They stand on the forest path filming themselves, framed against forest only.

They are NOT looking at the lens — their head is turned away to their right, eyes fixed on something well off-frame.

Their left hand is raised and pressed flat over their mouth.

They hold this, breath held, then let out one quiet uneven exhale through the nose and blink once slowly.

Their hair and loose front strands lift and settle in the wind.

At the very end their eyes flick briefly toward the lens without their head following, and they begin to move the phone.

EXPRESSION LOCK (0.0–2.6 s)

Surprise sliding into fear, and kept deliberately small.

This is a real person mid-realisation, not a reaction shot.

Correct:
eyes only moderately open — a normal alert width with the upper lid raised only slightly past neutral.

Brows lifted slightly and pulled a little together at the inner ends.

A small vertical tension line between the brows.

The gaze fixed and unmoving on the off-frame point.

Jaw slack behind the hand pressed flat over the mouth.

A tiny swallow.

Across the two and a half seconds the read shifts subtly from puzzled surprise toward dawning fear — brow tension increases slightly, eyes narrow a fraction rather than widening further, and shoulders draw up a little.

Forbidden:
wide staring eyes, whites visible all around the iris, eyebrows arched high, mouth stretched open behind the hand, gasping, flared nostrils, frozen shocked mask, any expression held or aimed at the lens.

If the eyes look larger than their normal relaxed eye shape by more than a small margin, it is wrong.

They never look at the lens in this beat — not once, not even a flick until the final few frames.
2.6–3.4 s — ROTATION.

They swing the phone 180 degrees to face forward.

Heavy lateral motion blur, a smear of grey and green, rolling-shutter skew bending the trunks, and a hard auto-exposure lurch as the bright fog and pale sky enter frame.

The image briefly blows out, then settles down over about half a second.

3.4–5.2 s — REAR CAMERA, WIDE.

The forest gap opens ahead:

dark trunks converging left and right, wet mossy floor at the bottom, ranks of fogged spruce, and the grey limestone cliff 300 m away with the huge black cave arch in the upper-middle band.

Handheld drift.

They begin a slow pinch-zoom in on the cave, the frame stepping up to roughly 2× over about a second, softening and losing resolution as it magnifies, with a brief focus hunt before it locks.

The arch now fills more of the frame, its blackness absolute.

5.2–7.4 s — THE EMERGENCE.

Inside the black arch, a shape resolves out of the mist.

A colossal hand comes up and grips the upper lip of the cave mouth from inside — a dark grey mass curling over the rock edge, fingers not individually readable.

Immediately several small rocks and a shower of grit break loose from the arch's upper edge and fall down the cliff face, small at this distance, tumbling and deflecting off ledges, with faint dust puffs where they strike.

Then the giant hauls himself forward and out, stooping low and tilting his head noticeably to the side to clear the top of the arch.

The duck must be obvious and must read as a body barely fitting through the opening.

He straightens partly, staying hunched, one hand still on the rock, and stands in the mouth of the cave:

a soft-edged featureless dark grey silhouette, head low, shoulders rolled, long arms hanging, legs lost in the mist layer.

His single eye reads as a pale near-white ring with a hard bright glint at its centre — the only bright mark on him.

7.4–9.2 s — HE TURNS TO THE LENS.

He holds still for a beat, head oriented forward and slightly down, scanning the forest.

Then his head rotates slowly and deliberately, and stops — facing directly at the camera.

The pale eye-mark swings around with the head and lands square on the lens, the glint sharpening as it catches the flat light head-on.

He does not move again.

He simply looks.

As he emerged, the treetops in the mid-distance around the cliff base shudder and sway, and three separate loose groups of dark bird silhouettes burst up out of them, scattering fast and low across the grey, calling.

The handheld frame twitches — the main character's hands have jolted.

9.2–10.2 s — ROTATION BACK.

They swing the phone 180 degrees back to their face.

Fast messy blur, rolling-shutter skew, exposure lurching down as the darker forest and their face fill frame.

10.2–13.6 s — FRONT CAMERA, LOOKING FOR A WAY OUT.

Their face fills more of the frame now, closer and less stable, still with forest behind them.

The restrained surprise has become restrained fear:

jaw set, lips slightly parted, breathing shallow and visibly quicker, eyes alert but not staring, brows drawn together, a small swallow, tightness around the mouth.

Their left hand has dropped from their mouth.

They are not looking at the lens at any point.

They turn their head sharply LEFT and scan past the trees, eyes moving faster than their head, searching.

Then they turn sharply RIGHT and scan that way.

Under this, the image begins to shake in a low rhythmic pulse — the ground itself is trembling, each tremor arriving as a distinct thud roughly every 1.4 seconds, growing slightly stronger and closer.

Loose needles and small debris shiver on the ground behind them.

The trees behind them sway more than the wind alone would explain.

At about 12.6 s they start to turn their head LEFT again — and stop dead.

Their eyes snap up and forward, past the camera, focusing on something high and approaching.

Their face goes still.

Then, quietly and with real desperation rather than volume, they say in clear English:

"Oh my God."

Their voice cracks slightly, barely above a breath.

Behind them, deep in the fog, a large dark shape has become faintly visible between the trunks, soft-edged and grey, with a single pale eye-mark high on it.

13.6–15.0 s — FINAL ROTATION.

They swing the phone sharply away from themselves again.

Violent motion blur, skewed trunks, exposure lurching bright — and the clip cuts on that blur.

PERFORMANCE LOCK — RESTRAINED EMOTION (important)

Their fear and surprise must be underplayed at every moment.

Correct:
moderately open alert eyes, brows slightly lifted and drawn together, shallow quick breathing, a hand over the mouth, a swallow, a small unsteady exhale, tension around the jaw, eyes darting faster than the head, one voice crack.

Forbidden:
screaming, mouth stretched wide, whites showing all around the iris, exaggerated gasping, over-articulated brows, trembling lower lip, tears, theatrical head-clutching, any pose held for the camera, any performance aimed at the lens.

They never look into the camera and never play to it.

They read as a real person genuinely frightened and trying to stay quiet — nervous, alert, and slightly frozen.
PHYSICS

Giant's movement:
enormous mass with correct inertia — slow to start, slow to stop, the hand settling heavily onto the rock, the body hauling forward against its own weight, the head rotating with a slow steady sweep and a small settle at the end.

No fast or light movement anywhere.

His steps land with a real transfer of weight.

Ground tremor:
each footfall arrives as a discrete low impulse that shakes the camera, the trees, and loose ground debris, with correct delay between the visible shake and the audible thud given a distance of a few hundred metres closing steadily.

The interval stays consistent at roughly 1.4 seconds, each impulse slightly stronger.

Falling rock:
the stones dislodged from the arch lip fall with real gravity, tumble irregularly, strike ledges and deflect, and vanish into the fog, with small dust puffs on impact.

Birds:
real flight — a sudden explosive burst upward out of the canopy, fast irregular wingbeats, scattering in different directions rather than as a neat flock, silhouetted and quickly lost in the fog.

Fog:
physically correct volumetric density increasing with distance, softening every edge beyond about 40 m and flattening contrast progressively, drifting slowly in the wind.

Cloth and hair:
the main character's clothing and hair move with real weight.

The jacket, shirt, trousers, and accessories respond naturally to the wind and movement.

Hair lifts and settles continuously, strands crossing the face naturally.

BACKGROUND ANIMATION — FULL REALISM

A medium, steady wind at 6–8 m/s moving across the frame.

The main character's hair is constantly in motion — strands lifting off the shoulders, loose front pieces blowing across the cheek and catching near the mouth, fine flyaways moving around the hairline.

If a cap is present in image_1, it stays on naturally and responds subtly to the wind.

The spruce and fir behind and around the main character sway visibly and continuously — crowns leaning through 6–10 degree arcs on a 2–3 second rolling period, main boughs lifting and dropping, needle clusters flickering, gusts rolling through the stand as travelling waves so no two trees move in phase, silhouettes constantly reshaping.

Ferns, grass, and low undergrowth on the forest floor bend hard and spring back in each gust, in visible travelling waves.

Loose needles, small twigs, and leaf debris are carried across the frame in continuous streams, denser during gusts.

The fog drifts slowly and unevenly, thickening and thinning in slow bands, occasionally veiling and revealing the cliff face and the arch.

The mist band across the lower part of the cave mouth curls and shifts.

Water beads on needles and ferns; everything is visibly damp.

Distant unseen birds cross the grey in ones and twos before the main burst.

The light level stays flat and constant — no sun breaking through, no shadows appearing.

Nothing in the frame is ever static.

LIGHTING

Flat, diffuse, overcast daylight at roughly 7500–8500K from directly above through a thick cloud layer.

No visible sun, no directional shadows, no sunbeams, no warm light anywhere.

The main character's face is lit softly and evenly from above with gentle shadow under the brow, nose, and chin, and a cool blue-grey cast overall.

Luminance falls off strongly with depth:

the near trunks are the darkest values, the mid forest steps lighter with each fog layer, the cliff sits lighter still, and the sky clips slightly bright.

The cave interior is the darkest value in the frame.

The giant's silhouette sits only slightly darker than the fog around him.

His single eye-mark is the brightest small point in frame.

Phone auto-exposure visibly rides throughout — brightening as they pan into the dark forest, pulling down when the pale fog and sky fill frame, with a short lag each time.

AUDIO

Continuous wind across the phone microphone, gusting and occasionally overloading into soft distortion.

Wind moving through spruce needles.

The main character's breathing, close and shallow on the front-camera beats, quickening after the rotation back.

Small unsteady exhales.

Fabric rustle from clothing against the mic.

Wet footfalls shifting on the forest floor.

At 5.2 s:
a distant deep grating sound of rock under enormous pressure, and the small dry clatter of falling stones arriving a beat late.

From 7.4 s:
birds erupting — a burst of wingbeats and sharp alarm calls, fading fast.

From 10.2 s:
deep, low, resonant footfalls arriving roughly every 1.4 seconds, each one felt as much as heard, growing louder and closer, with a subsonic thud and a following rumble through the ground and the trees.

At 12.9 s:
their voice, quiet, cracked, desperate, in clear English:

"Oh my God."

Barely above a breath, not shouted.

No music.
No score.
No sound design flourish.
No other voices.

FULL SCENE INTEGRATION LOCK

Everything in frame is physically present in the same real location, not composited.

The main character stands on real ground with correct contact and weight.

The giant is genuinely 300 m away inside the real cave, occluded by real mid-distance treetops, sitting behind the same volumetric fog as everything else at that depth.

His contrast, colour, edge softness, and noise level match the cliff face beside him exactly.

He is never sharper, never darker, never more saturated, and never more detailed than the rock at the same distance.

His falling stones interact with the real cliff.

The birds come out of the real canopy.

The tremor shakes the real camera, real trees, and real ground debris together.

The wind moving their hair is the same wind moving the trees.

Grain, noise, compression artefacts, exposure behaviour, and colour grade are identical across the main character, forest, cliff, and creature.

No cutout edges, no halos, no rim separation, no cleaner-looking element against a softer plate.

POSITIVE CONSTRAINTS

The phone is never visible — no phone body, no hand holding a phone, no screen, no reflection, no UI, no overlays, no recording indicator, no timestamps, no app graphics.

The image is only what the lens sees.

In the first beat the cave and cliff are completely OUT of frame — only forest is behind them, and their eyeline exits the frame to their right and slightly up.

No rock face, no arch, not even partially, not even in fog at the frame edge.

Their expression stays restrained throughout.

No exaggerated fear.
No screaming.
No theatrical reaction.

They NEVER look into the camera lens.

The main character's face in every frame is exactly the face and identity from <<<image_1>>>.

No other face.
No blended face.
No identity drift.

Their clothing, hair, accessories, and physical appearance exactly match <<<image_1>>>.

If image_1 shows a male character, maintain the male identity and adapt clothing naturally while preserving the same style.

If image_1 shows a female character, maintain the female identity exactly.

If glasses exist in image_1, keep them.
If glasses do not exist in image_1, do not add them.

They say only:

"Oh my God."

in clear English, quietly and with a cracked voice, at approximately 12.9 s.

Camera order is exact:

front camera → 180° swing → rear camera with a slow 2× pinch-zoom → creature emerges and turns to lens → 180° swing back to front camera → they search left, then right, then freeze looking up and forward → final 180° swing that ends the clip.

The giant grips the upper edge of the cave mouth, ducks and tilts his head to fit through, and stoops as he comes out.

The tight fit against the 24 m arch must be obvious.

The giant is exactly 18.3 m with all listed proportions, matching <<<image_4>>>, with the human-scale relationship from the reference sheet preserved.

At distance the giant reads ONLY as a soft-edged featureless dark grey silhouette in dense fog, roughly one stop darker than the mist behind him.

No skin detail.
No wrinkles.
No muscle definition.
No colour.
No flesh tone.
No highlights.
No readable fingers.
No visible loincloth detail.

Passing mist partially swallows parts of him.

The single exception is his eye:

a pale near-white ring with a hard bright glint, the only bright mark on him and the brightest small point in frame.

No glow.
No emissive light.
No flare.
No visible iris colour.

Exactly ONE eye.
No second eye.
No socket.

Rocks fall from the arch lip when he grips it.

Treetops shudder and three separate groups of bird silhouettes burst out of the canopy as he emerges.

The ground trembles with discrete footfalls from 10.2 s onward, shaking camera, trees, and ground debris together, each thud roughly 1.4 seconds apart and growing closer.

Location exactly matches <<<image_3>>> — same fogged spruce forest, same grey limestone cliff, same enormous black cave arch, same cold overcast palette.

Nothing added.
Nothing invented.
No people other than the main character.
No animals other than the distant birds.
Nothing man-made.

Cold, desaturated, overcast grade throughout — blue-grey, near-black, muted green, pale grey.

No sun.
No shadows.
No warm tones.

The environment is fully alive:

medium wind moving hair and all vegetation with wide-arc out-of-phase sway, undergrowth bending in travelling waves, debris streaming across frame, fog drifting and veiling, everything damp.

Nothing frozen or static.

Full photographic realism and real phone-camera behaviour:

genuine handheld tremor, rolling-shutter skew on fast pans, auto-exposure hunting, autofocus searching, digital noise in shadows, compression softness in the fog, resolution loss on zoom.

No cinematic stabilisation.
No film grain.
No anamorphic flares.
No colour grading flourish.

No text.
No captions.
No subtitles.
No logos.
No watermarks anywhere in frame.

28723 / 50000

Reference Images (Optional)

Aspect Ratio

Duration

Resolution

Generate Audio2x creditsBasic+

Required Credits50

Video Preview