AI video generator

AI Video Generator

Describe a shot, drop in a photo or a reference clip, or cast a character you've saved, and generate a finished video with sound in a couple of minutes. The composer below is the real product: pick a preset instead of a model, see the exact credit cost before you commit, and keep everything in a private library until you decide to publish or remix.

0/2000
Style
Aspect
Duration
Audio
Quality

Sign in to see your credit estimate. Creating needs a plan, from $4.99 a week.

One composer, every starting point

The same panel handles every way a video can begin. Attach what you have; the router picks a model that supports it.

Create from text

A sentence is enough. The prompt enhancer can expand it with camera, lighting and pacing vocabulary without changing your idea.

Create from an image

Upload a photo as the first frame. Add a second image as the last frame to animate a precise transition.

Create from a reference video

Guide motion, framing or style with a clip you already have, then describe what should change.

Use a saved character

Cast a character you set up once, from a few reference photos, and keep the same face and outfit across every scene.

Generate audio

Presets with native audio produce ambience, effects or dialogue in the same pass; you can also attach a music or voice track.

Remix and transform

Restyle existing footage, swap the subject or change the environment while preserving motion.

How it works

  1. 01

    Describe or attach

    Type the shot, or start from an image, clip or character. Vertical 9:16 is the default; 16:9 and 1:1 are one tap away.

  2. 02

    Pick a style, not a model

    Auto, Fast, Cinematic, Story, Character or Ultra. Each preset changes routing, defaults and price.

  3. 03

    Check the quote and generate

    The credit cost for the routed model appears before you confirm. Credits are reserved, then charged only on success.

  4. 04

    Download, publish or remix

    The finished clip lands in your library at full resolution. Publish to the feed, keep it private, or send it straight into a remix.

Style presets

Presets are the only model decision most people need to make.

PresetOptimised forTypical trade-off
AutoWhatever the request needsBalances quality, speed and cost
FastDrafts and iterationLower resolution, quickest turnaround
CinematicRealism, lighting and native soundSlower, higher credit cost
StoryMulti-shot sequences with cutsBest with prompts that describe beats in order
CharacterIdentity-locked scenes with your saved charactersRequires at least one character attached
UltraMaximum fidelity, up to 4K where supportedPro plan, highest cost

How model routing works

You never have to read a model comparison to make a clip. Each request is scored against every enabled model in our registry using the capability it needs (text-to-video, image-to-video, first-and-last frame, reference video, character reference), the preset you picked, the aspect ratio and duration, and the model's live health. The best match is submitted; the next best are kept as fallbacks.

Costs are computed the same way. The quote you see before generating is the price for the model that will actually run, including any resolution or audio surcharge, and it is reserved rather than charged until the clip completes.

Models behind this generator

Live from the registry. Availability and specs update as models change.

Veo 3.1

Premium maximum-quality video with native audio.

audioup to 8s4k2 refs

Seedance 2.0

Balanced cinematic video with strong motion and reference support.

audioup to 15s4k9 refs

Gemini Omni

Character-consistent video from reusable references.

audioup to 10s1080p7 refs

Kling 3.0

Narrative multi-shot video generation.

audioup to 15s4k

Wan 3.0 Prime

Fast, low-cost video for quick iterations.

up to 10s1080p4 refs

Example prompts

Click one to load it into the composer.

What people make with it

  • Short-form content for TikTok, Reels and Shorts
  • Product teasers and ad variations
  • Concept trailers, mood films and storyboards that move
  • Music visualisers synced to a track
  • Serialised stories with a recurring character
  • Talking-head explainers from a single portrait

Private by default, publishable in one tap

Private library

Every creation is stored privately with its prompt, settings and model, so you can rerun, tweak or download it later.

Visibility controls

Publish as public, followers-only, unlisted or private, and decide whether others may remix.

Downloads

Full-resolution files, permanently hosted on our storage, downloadable from the library at any time.

Remix lineage

If you do publish, remixes credit you and appear under your original.

Start from a template

All templates →

Frequently asked

How long does a video take to generate?
Fast presets usually finish in well under a minute. Cinematic, Story and Ultra clips take longer because they run heavier models at higher resolution. You can leave the page; the library and the bell notify you when a clip is ready.
What lengths and formats are supported?
Clips run from 4 to 15 seconds depending on the routed model, in 9:16, 16:9 or 1:1, at 480p to 4K where the model supports it. The composer only offers values the routed model can actually produce.
What happens if a generation fails?
The reserved credits are released back to your wallet immediately. If the failure was on the provider side and a fallback model can serve the same request, the router retries automatically and you are still charged once.
Can I use the results commercially?
Content you generate is yours to use, subject to our terms and community guidelines. You are responsible for any third-party material you upload as a reference, including people's likeness, brands and music.
Do I have to pick an AI model?
No. Choose a style preset such as Fast, Cinematic or Story and the router selects the best available model for that intent, aspect ratio, duration and the inputs you attached. If a model is degraded, the router falls back to a comparable one without charging you twice. Advanced users can still pin a specific model.
How much does a generation cost?
Every generation is quoted in credits before you confirm, based on the routed model, duration and resolution. Credits are reserved when you start and released automatically if the generation fails, so you only pay for what completes. Plans start at $4.99 a week and include a credit allowance; subscribers can top up with credit packs.
Are my generations private?
Yes by default. Everything you generate lands in your private library. You decide per creation whether to publish it to the feed, share it unlisted, restrict it to followers or keep it private, and whether others may remix it.
Can I download the videos?
Yes. Every completed generation can be downloaded in full resolution from your library. Files are stored permanently on our own media storage, not on the provider's temporary links.

Ready when you are.

Plans from $4.99 a week. Publish when you're proud of it.

Generate