The ink you have · The idea you are weighing · A preview in seconds
The hardest part of a cover-up is imagining it. Upload the old ink, describe the piece you are considering, and see whether it actually swallows the shape underneath or just sits beside it.
Our own run on this site's engines. Drag the divider and look for the band: the point of the demo is that you cannot find it, and that the new piece needed considerably more room than the old one occupied. Every output is AI-generated; what your ink allows is a question for your artist.
Drag to compare before and after
It takes a photo of the tattoo you want gone and renders a proposed new piece over it — dense enough to absorb the old shape, extended past its edges, shaded to your photo's own light.
Cover-up searches come with a mood the rest of the tattoo world does not have. Nobody browsing here is excited; they are stuck with a name, a faded tribal band, or a piece from an artist they now know was bad, and they have been told by the internet that their only options are a decade of laser or an enormous black shape.
Both of those claims are half true, and neither is answerable in the abstract. What settles it is looking at the actual arm with an actual candidate on it.
The pair on this page is our own run and it shows the real constraint honestly. The before is an aged tribal band, edges blown out, black faded to blue-green — the classic cover-up problem. The after is a layered blackwork peony that runs several centimetres past the band on every side, with the heaviest shading landing exactly where the old ink was.
Notice what it is not: it is not the same size as the original. That growth is not artistic licence, it is the arithmetic of covering ink with ink.
Where this stops being reliable: it renders a plausible cover-up, not a guaranteed one. Whether your specific ink can be covered depends on how deep and how dark it is, how the skin healed, and how much your artist can lift with a session or two of laser first. Treat every preview as a proposal to test against a professional — and if part of your plan is removing rather than hiding, see what erasing it looks like as the other half of the same decision.
Creative engine
Photograph the existing tattoo, describe the piece you are weighing, generate.
Any preview that covers old ink with something small or pale is lying. The useful ones look heavier than you hoped.
Floral, geometric, blackout — run all three on the same photo and the choice narrows itself in a couple of minutes.
Photograph the problem properly and the proposals get far more useful.
Even daylight, the limb square to the camera, the whole piece in frame with several centimetres of clear skin around it. That surrounding skin is where the new design has to go, so leave it in the shot.
"Dense blackwork florals", "heavy geometric mandala", "dark botanical with stippled shading" — styles carry the weight information a specific subject does not. Add "must fully cover the existing tattoo" and say what the old piece is.
If the old outline is still visible in the render, ask for more solid black and a larger footprint and run it again. The version that finally works is the honest answer to how big this has to be.
Three situations, one awkward tattoo each.
A relationship ended and the lettering did not. Script is one of the easier things to bury because it is thin and linear — see which shapes eat it cleanly before you resign yourself to a full blackout.
A tribal band or barbed wire, faded to blue-green, bought at nineteen. These need weight rather than size, and previewing a few dense candidates is the fastest way to see which style actually has it.
Wobbly lines, patchy fill, an artist you should not have trusted. Sometimes the answer is a rework rather than a cover — and comparing a preview against what the design looks like as clean linework tells you quickly which conversation to have.
What people ask before booking a cover-up consultation.
Not any tattoo with any design. Dense black, heavy saturation and scar tissue all restrict what will sit on top, and a few sessions of laser lightening first is a normal part of the plan rather than an admission of defeat. A preview shows you the ceiling of what is plausible; only an artist looking at the actual skin can confirm it.
Because that is how covering ink works. New pigment goes over old, so the fresh design has to be darker in the overlap and needs clear skin around it to read as a shape at all. If a preview comes back the same size as the original, it has not solved the problem — it has drawn next to it.
It renders them, and you should be sceptical of the result. Colour over old ink shifts unpredictably depending on what is underneath — a red that looks right in a render can go muddy on skin that already has green in it. Use colour previews to discuss direction with an artist, not to set expectations.
Yes. Add their drawing next to your photo and ask for that design placed over the existing tattoo. This is the most useful thing on this page: it turns their sketch on paper into a picture of your own arm, which is the version you can actually judge.
Bring them as direction, not as a brief. Artists who specialise in cover-ups work from what the old ink allows, and a render that ignores that will get politely rewritten. Saying "this weight, this density, roughly this footprint" is far more useful than handing over a picture and asking for it exactly.
It travels over HTTPS for the edit and stays in your own history until you delete it. It is never used to advertise. Every output is AI-generated.
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 — eleven 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 2.5 | The long-take tier, priced per second: 5s 480p ≈ 211 credits, 5s 720p ≈ 473. A full 30s take runs ≈ 1,260 at 480p and ≈ 2,835 at 720p. Supplying a reference clip lowers the per-second rate. |
| 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. |
Hide it, erase it, or preview the replacement.
Upload the piece you regret, weigh three candidates on your own arm, and walk into the consultation with something to point at — or [see it erased instead](/image/remove-tattoo-from-photo).
A real edit made with this tool — drag your own photo in on the left, the prompt is already written, then press Generate.
