AI Reels Generator One vertical clip, 4 seconds

Putting this second rather than in the FAQ, because it decides whether the next two minutes are worth your time. A reel that performs is usually 15 to 60 seconds, cut from several shots, carrying a track people recognise and captions that work with the sound off. This page gives you one continuous 4-second shot, no captions, and whatever ambient audio the model generates.

So it is a component, not an output. It is genuinely useful as one: an opener before your talking-head footage, a B-roll insert, a loop for a story, a test of whether a still you own reads well in motion. It is not something you post as a reel on its own and expect to hold anyone.

If a finished vertical video is what you came for, the honest answer is that our video tools do that and this page does not — longer clips, your own prompt, several generations you can cut together. Same account, same credits. We would rather tell you now than after you have waited.

One more thing the example shows: the shape comes from your photo. Upload a tall photo and you get 9:16; upload a square and you get a square clip, because nothing is cropped or added. Vertical framing also invites the model to build depth behind the subject — in our own run a plain studio wall became a lit room, which flatters a vertical clip and is still the model reinterpreting your background rather than preserving it.

Signing up gives you 20 credits and one clip at the default tier costs 20 at list price, so the first one is free — no card, no trial period, no plan to cancel. After that each clip is billed per generation. A free tier is not something we have, and calling the signup credits one would be a lie you would find out about on your second clip.

Failed and cancelled runs refund automatically, so a photo the model cannot use does not silently consume your one free attempt — and when a run does fail, trying again with the same photo is usually a better first move than looking for a different one.

The free clip carries a watermark, which matters more here than on our other pages: a watermark in the corner of something you post is a real cost. Watermark-free exports come with a paid plan.

Use photos of yourself, or of people who agreed to appear in a clip — and if you are posting it, they need to have agreed to that too. Animating a stranger, a celebrity, or someone who never consented is non-consensual synthetic media; do not use this for that. Never use photos of minors.

Face compliance runs automatically on every generation, which is why nothing has to be registered first. But an automated check is a floor, not permission: it cannot know whether the person in your photo agreed, and neither can this page.

Your uploads are not a gallery. Nothing is stored until you sign in, generations are private to your account, and the photo you upload is used for that generation rather than added to a public feed.