One pet photo in · Beams that light the room · Nothing to install
Two crimson beams, fired from your own dog or cat's eyes, with the red light landing on the floor behind them — online, free to start, no editor to learn.
A real run through the model this page uses, on an ordinary living-room photo. Drag the divider and watch the rug: the red bounce arrives with the beams, which is the difference between a lit scene and a sticker. Every output is AI-generated, so your result varies with your photo and how clearly the eyes read — treat this as a guide to what the tool can do, not a fixed result you will get back exactly.
Drag to compare before and after
It takes one ordinary photo of your animal and shoots two glowing beams out of their eyes toward the camera, then relights the frame as if that actually happened. The laser-eyes look started as a human meme and moved to pets, which is where it stayed — a cat with a flat stare is funnier with beams than any person is.
Two things separate a good one from a bad one, and neither is the beam itself. The first is where the beams start: they have to leave the pupil, at the angle the eye is actually pointing, or the animal reads as looking one way while firing another. The second is spill — a real beam that bright would bounce off the muzzle, the rug and the wall behind, and without that bounce the whole thing looks like a sticker somebody dragged on.
The beam pass runs on the Nano Banana image model, in the browser, with free credits to start. Upload the photo — the flow defaults to image-to-image — pick your format, and the credit estimate updates before you commit; a failed run is refunded automatically unless it broke the content policy. Result quality comes down to one thing: whether the eyes are open and facing you.
A head-on shot with both eyes visible gives the model two clear origins to fire from. A profile shot, a squint, or eyes lost in shadow give it nothing to anchor to, and the beams end up floating somewhere near the face instead of coming out of it.
Creative engine
Upload a photo where the eyes are visible, say how intense you want the beams, and the credit estimate updates before you generate.
Crimson beams with a hot white core, plus the red bounce they throw onto fur, floor and wall — the part a pasted overlay never has.
Runs in the browser with free credits — no editing app, no timeline, no account wall before you see a result.
The same one-photo, one-pass idea runs across the studio: a portrait of the same animal in the pet portrait generator, a caption instead of a beam in the speech bubble meme generator, or a whole invented face in the AI baby generator.
From one pet photo to a lit frame, with the cost shown before you commit.
Get your animal looking toward the camera with both eyes open and unshadowed. Eyes the model cannot see are eyes it cannot fire from.
Ask for thin precise beams or wide room-filling ones, red or another colour, and whether you want the spill dialled up or kept subtle.
Generate, then post it. A failed run is refunded unless it broke the content policy, so trying a second colour costs you nothing.
People posting their pet, people making a group-chat reply, people printing something silly.
Give the recurring character on your feed the one shot that always performs, without opening an editor between the photo and the post.
Some conversations only have one correct answer, and it is your own cat with beams coming out of their face.
A mug, a sticker sheet, a birthday card for someone who loves this animal more than they love most people.
Common questions about firing beams from a pet photo with Kavel.
No, and that is mostly why people arrive here. The usual answers to this are timeline apps where you install the software, sign in, and hand-place a glow on each eye. This runs in the browser with free credits to start — you upload the photo and the beams come back already positioned.
Yes, and on most animals whose eyes read clearly in the photo. Cats tend to look better because the flat unimpressed stare is already halfway to the joke. What matters is not the species but whether both eyes are open, facing you and out of deep shadow.
Because the eyes in the photo were not pointing at the camera. The beams are fired along the direction the pupils are actually looking, so a head turned three-quarters away sends them off to the side. Reshoot with your animal looking straight down the lens and the problem disappears.
Yes — say it in the prompt. Red is the default because that is the version of this meme people recognise, but blue, green, purple and white all work, and so does asking for a thinner or wider beam. Each variation is a fresh run, and runs take seconds.
It should not. The pass is meant to add the beams and the light they cast and leave everything else — fur, markings, ears, pose, background — untouched. If a result comes back with the muzzle redrawn or the markings shifted, run it again; the model is not deterministic and a second pass usually behaves.
A head-on shot in even light where both eyes are wide open and you can see the pupils. Dim rooms, backlight, a squint mid-blink, or a heavy crop that leaves no wall behind the animal all hurt — the last one especially, because with nothing behind them there is nowhere for the red bounce to land, and the bounce is what sells it.
The estimate appears before you generate and updates with the format and resolution you pick, so you see the cost first. Failed runs are refunded automatically unless they broke the content policy, and new accounts start with free credits — enough to fire a few rounds before spending anything.
Read the terms for the current position on outputs before putting one on merchandise you intend to sell. For a post, a print for yourself or a card for a friend there is nothing to think about; a product listing is a different question and worth checking rather than assuming.
One credit pool covers Nano Banana images and Seedance and Veo video. The cost shows before every run, and failed jobs are not charged. Use a subscription for ongoing work, or a one-time pack when you just need to top up.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
One-time top-ups — buy extra credits any time you run low.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
Charges appear as “KAVEL AI” on your card statement. You can cancel any time from Settings → Billing; cancellation takes effect at the end of the period you already paid for.
Powered by
Use one balance across every supported image and video model — ten of them today, listed below — and check the credit cost before each request.
Video models
Image models
Model credit guide
You're only charged for successful generations. The exact estimate in the generator varies by model, length, resolution, audio, and number of images.
| Type | Model | Credit cost |
|---|---|---|
| Video | Seedance 2.0 | 5s 720p image-to-video ≈ 188 credits; text-to-video ≈ 308 credits. Scales with resolution and length. |
| Video | Seedance 2 Fast | Faster and lower cost. 5s 720p text-to-video ≈ 248 credits. |
| Video | Seedance 2 Mini | The cheapest Seedance tier. 5s 720p ≈ 154 credits, 5s 480p ≈ 72 credits. |
| Video | Seedance 1.5 Pro | Audio doubles the rate. 5s 720p ≈ 27 credits silent, ≈ 53 with audio; 1080p ≈ 57 and ≈ 113. |
| Video | Veo 3.1 | Billed per video, not per second (Lite tier). About 45 credits at 720p and 53 at 1080p. |
| Video | Kling 3.0 | Audio raises the rate. 5s 720p ≈ 105 credits silent, ≈ 150 with audio; 1080p ≈ 135 and ≈ 203. |
| Video | MiniMax H3 | Fixed 2K, no resolution ladder. Priced per second — a 5s clip ≈ 158 credits. |
| Image | Nano Banana 2 | Generate or edit from text and images. About 8 credits per 1K image, 12 at 2K, 18 at 4K. |
| Image | Nano Banana Pro | Consistent run times across generations. About 12 credits per 1K or 2K image, 21 at 4K. |
| Image | Nano Banana 2 Lite | Faster, simpler variant. A flat 8 credits per image at every resolution. Start here to test. |
| Image | GPT Image 2 | The lowest-cost image model here. About 3 credits per 1K image, 6 at 2K, 12 at 4K. |
| Image | Seedream 5.0 Lite | Flat pricing — about 8 credits per image whether you generate or edit. |
Other ways to put your own photo through a single pass, and the models behind them.
Two beams, your own dog or cat, and the red light landing on the floor behind them. No editor to learn and nothing for your pet to sit through.
A real edit made with this tool — drag your own photo in on the left, the prompt is already written, then press Generate.
