Skip to content

AI video generator from text or a photo

Describe a shot or upload a first frame. Pick Seedance 2.5, Kling 4.0, Veo 3.1 or another model, and get the clip.

Make a video
  • From $19 a month or $190 a year
  • Up to 30 s per take
  • Up to 4K
  • Sound with the picture
  • Kling 4.0
  • Seedance 2.5
  • Kling 3.0 Omni
  • MiniMax H3 Max
  • Gemini Omni Flash 1.1
  • FLUX.3

How do you make an AI video?Start from words or from a photo

A breakdancer in a red tracksuit spins on one hand in an empty parking garage at night
Kling 4.0 · 8 s · text only
Text to video

Write the shot, beat by beat

Name the subject and the place, then the camera, what happens in each stretch of seconds, the light and the sound. This is the whole prompt behind the clip.

Prompt
Subject
A breakdancer in a faded red tracksuit spins on one hand on the concrete floor of an empty parking garage at night.
Camera
Camera: handheld, slowly orbiting him at floor level, about a quarter circle over the whole shot, with subtle bob and a slightly late reframe when he moves.
0 to 3 s
0-3s: he drops from standing into a fast windmill, his legs sweep in wide circles, the tracksuit fabric snaps and ripples.
3 to 6 s
3-6s: he kicks up into a one-handed freeze, holds it, his arm trembles under his body weight.
6 to 8 s
6-8s: he drops out of the freeze, lands on his feet and steps back breathing hard, a friend off frame claps.
Physics
Physics: real body weight, his palm presses and slides on the gritty floor, chalk dust and grit kick up, the jacket swings with momentum and settles.
Light
Lighting: one sodium-vapour light overhead and green-white fluorescent strips in the background, deep shadows between concrete pillars, wet patch on the floor reflecting the lights, fine film grain, low-saturation grade.
Sound
Audio: sneaker squeak, fabric whip, breathing, echo of the garage, a car passing on the street outside.
Leave out
No background music. No subtitles.
Image to video

Your photo is the first frame

Upload a photo, then write what moves and how the camera moves. Add a second image and most models end the clip on it.

“She turns to face the camera and throws her arms wide as the train thunders onto a high steel bridge over a deep canyon. The camera pulls back into a wide aerial shot that ends on the whole train crossing the bridge. <The train horn blasts>, wheels hammering the rails, wind roar. Her mouth stays closed, no narration.”

Seedance 2.5 · 8 s · 480p · sound on

She turns, throws her arms wide, and the train crosses a high steel bridge over a canyon as the camera pulls back into a wide aerial view
A woman in a long rust-red coat stands on the roof of a silver train racing across a red desert at golden hour

The photo it starts from

She turns, throws her arms wide, and the train crosses a high steel bridge over a canyon as the camera pulls back into a wide aerial view

Which AI video model is best?Every model on one scale

Each bar spans the lengths one take can run. Pick what your shot needs and the models that can do it light up.

14 models

  • Seedance 2.5Default

    People talking on camera, with lip sync

    4 to 30 sTop 1080pSound On or off

  • Kling 4.0

    Action and physical motion

    3 to 30 sTop 1080pSound Always on

  • Wan 3.0

    Many references at a low price

    2 to 30 sTop 1080pSound On or off

  • FLUX.3

    Clips that match FLUX.3 stills

    5 to 20 sTop 1080pSound On or off

  • LTX-2.5

    Long single clips with preset camera moves

    6 to 20 sTop 1080pSound On or off

  • Vidu Q3

    Very short clips and anime motion

    1 to 16 sTop 1080pSound On or off

  • Seedance 2.0

    4K clips from image and clip references

    4 to 15 sTop 4KSound On or off

  • Kling 3.0

    Realistic motion from a first to a last frame

    3 to 15 sTop Standard or ProSound On or off

  • Grok Imagine 1.5

    Short clips with sound

    1 to 15 sTop 1080pSound Always on

  • MiniMax H3 Max

    Matching the motion of a reference clip

    5 to 15 sTop 768pSound Always on

  • Hailuo-03

    2K clips with sound and dialogue

    5 to 15 sTop 2KSound Always on

  • Gemini Omni Flash 1.1

    Following reference clips and images

    3 to 10 sTop 4KSound Always on

  • Veo 3.1

    Cinematic realism with dialogue

    4, 6 or 8 sTop 4KSound On or off

  • Runway Gen-4.5

    Cinematic camera moves from a first frame

    5 or 10 sTop 720pSound Silent

For TikTok, YouTube or the big screenPick the shape before you generate

Every model on this page makes 9:16 and 16:9. Seedance 2.5 also makes 1:1, 21:9, 4:3 and 3:4. Start from a photo and most models keep its shape.

A highliner in an orange jacket crouches on a line between two granite spires above a sea of clouds at sunrise
9:16TikTok, Reels, Shorts
A highliner in an orange jacket crouches on a line between two granite spires above a sea of clouds at sunrise
1:1Feed posts
A highliner in an orange jacket crouches on a line between two granite spires above a sea of clouds at sunrise
16:9YouTube, websites
A highliner in an orange jacket crouches on a line between two granite spires above a sea of clouds at sunrise
16:9YouTube, websites
A highliner in an orange jacket crouches on a line between two granite spires above a sea of clouds at sunrise
21:9A film look
“A highliner in a bright orange jacket and a white helmet walks a thin line strung between two tall granite spires, high above a sea of clouds at sunrise, a leash clipped from her harness to the line. Halfway across, a gust hits: the line sways, she drops into a low crouch with both arms out wide, holds, then rises and walks on. The spires drop away sheer into the clouds far below, and the low sun turns the cloud tops gold. Realistic adventure film, one low sun against a cold blue sky. Wide shot from a ledge level with the line, framing her whole body, the far spire and the drop below; the camera slowly pushes in and ends on her standing tall in the middle of the line. Sound: <wind gusting past the rock>, <the line creaking>, <a carabiner clinking>. Her mouth stays closed, no narration, no music.”
Seedance 2.5 · 8 s · 480p · sound on · one run per shape

How long can an AI video be?Thirty seconds in one take, then keep going

  1. 01

    One take, up to 30 seconds

    Seedance 2.5, Kling 4.0 and Wan 3.0 make a single take of up to 30 seconds.

  2. 02

    Up to six shots in one run

    Write each shot on its own line and Kling 3.0 cuts between them, up to 15 seconds in all.

  3. 03

    Extend a clip

    Add a clip to Veo 3.1 and it continues the shot by 7 seconds. FLUX.3 extends a clip too.

  4. 04

    Join clips on a timeline

    Put clips in order on the Studio timeline and export one video.

  1. A street performer with a burning torch walks into a circle of young people in a smoky alley lit red

    Shot 1Wide shot. Night in a narrow city alley lit by a red neon glow. A street performer in a plain black sleeveless shirt walks into a circle of young people with a burning torch in his hand, smoke drifting through the light. A heavy hip-hop beat plays from a speaker and the crowd cheers.

  2. Close-up of the performer lifting the burning torch to his lips, firelight on his face

    Shot 2Close-up. He lifts the torch close to his lips and stares into the flame, firelight flickering on his sweaty face. The beat cuts out and the crowd goes quiet.

  3. From below, he blows a huge fireball into the night as the crowd throws their hands up

    Shot 3Low angle. He blows a huge roaring fireball up into the night air, and the orange light floods the faces of the crowd as they shout and throw their hands up. A loud whoosh of flame, then the crowd erupts.

Three shots in one Kling 3.0 run · 15 s · 16:9 · sound on

Simple pricing that scales with you.

Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.

Creator

$19/month

Billed monthly

For solo creators posting every week

500 credits every month

  • Up to 250 AI images
  • Up to 25 Seedance 2.5 clips
  • Up to 1.5 hours of AI voiceover
  • Roll over up to 1,000 credits

Pro

Most popular
$49/month

Billed monthly

For creators posting daily across channels

1,300 credits every month

  • Up to 650 AI images
  • Up to 65 Seedance 2.5 clips
  • Up to 4 hours of AI voiceover
  • Roll over up to 2,600 credits

Studio

$99/month

Billed monthly

For brands and production teams

2,700 credits every month

  • Up to 1,350 AI images
  • Up to 135 Seedance 2.5 clips
  • Up to 9 hours of AI voiceover
  • Roll over up to 5,400 credits

Scale

$199/month

Billed monthly

For agencies running always-on content

5,500 credits every month

  • Up to 2,750 AI images
  • Up to 275 Seedance 2.5 clips
  • Up to 18 hours of AI voiceover
  • Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights

Want checkout, comparison tables, or a custom volume? See the full pricing page

Before your first clipCommon questions

Picture the shot.Then make it.

Make a video

Plans start at $19 a month.

A breakdancer in a red tracksuit spins on one hand in an empty parking garage at nightA vintage truck sliding through a red rock canyon and throwing up dust
A lone rider crossing a cracked desert flat as a storm front rolls over the buttesA woman in a red dress walking through a field of tall wheat in low sun
A rancher in a felt hat leaning on a fence post with cattle behind himA trumpet player in a long coat playing in a neon-lit back alley at night