One photo in · A funny cartoon out · Free to try in the browser
An oversized head, playful exaggeration, and features your friends still recognise. It is the cartoon a street artist would draw, from a photo you already have.
A real caricature, drawn by the model this page runs on. Drag the divider to compare the original photo with the cartoon result. Every output is AI-generated, so your finished picture varies with your photo, your prompt, and the style you describe — 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
Exaggeration is the easy half; keeping the likeness through it is the hard one. One photo of you comes back redrawn as a funny cartoon — a playfully oversized head, stretched features, bold hand-drawn linework instead of camera detail — with the same person still reading through all of it.
Instead of hiring a street artist or fiddling with filters that just add outlines, you upload a clear picture and the model reads your features, pushes the ones that make you you, and colours the whole thing like an illustration while keeping you clearly recognizable. On Kavel the tool runs on the Nano Banana image model, so a party-ready cartoon finishes in one generation rather than a slow drawing session.
You start from your uploaded photo — the flow defaults to image-to-image — set the format and the resolution, and the credit estimate updates before you commit; a failed run is refunded automatically (unless it broke the content policy), so trying a second version costs nothing but time. The result suits a birthday laugh, a team page that needs personality, a share-worthy avatar, or a printed card for a friend.
And because the same studio also paints a portrait, turns a photo into a sticker, and sketches a shot, one workflow covers a whole range of styles without a separate app for each. Think of it less as a filter and more as a street artist who works in seconds — the exaggeration is bold, and the face grinning back is unmistakably yours.
Creative engine
Upload a photo, pick the vibe, choose the format and resolution, and the credit estimate updates before you generate.
Upload one clear photo and the model redraws you as a bold cartoon with an oversized head and lively illustrated colour.
Pushes your real features — the smile, the glasses, the hair — so the drawing stays recognizable rather than generic.
Set the format, check the credit estimate, and generate; a run that fails costs you nothing, so a second version is free to try. Exaggeration is the point here. The pet portrait plays the same joke straight-faced on an animal, and the oil painting portrait drops the joke and keeps the likeness.
From one photo to a big-head cartoon, with the cost shown before you commit.
Add one clear photo where your face and expression are easy to read. A big smile and clear features give the model the most to play with.
Steer it if you like — more or less exaggeration, a colour or black-and-white ink look, a prop or a background. Clear direction keeps the drawing on-brief.
Confirm the estimate, generate the cartoon, and download it. If a run fails, it is free, so you can adjust and try another version.
Leaving gifts, team pages, avatars that should not look too serious.
Turn the guest of honour into a big-head cartoon for a card, a poster, or a laugh in the group chat that always lands.
Swap a plain headshot for a playful drawing on socials or a gaming profile, an avatar with personality that still looks like you.
Give a company page a friendly, human feel with a matching set of drawn portraits instead of stiff corporate headshots.
Common questions about turning a photo into a fun cartoon with Kavel.
By default the head is enlarged and the standout features are pushed for a classic big-head look, on a smaller body. Want it milder or wilder? Say so in the prompt and the drawing follows. A failed or unwanted run takes seconds to redo.
Yes — that is the point. The exaggeration lands on the real features, so the smile, the glasses, the hair, and the face stay recognizable. A clear, expressive photo makes the likeness read strongest.
It is a full redraw, not a live filter. The model rebuilds you as an illustration with clean linework and flat colour rather than tracing outlines over your photo, so the output is a finished cartoon image you can download.
A sharp, well-lit, front-facing photo with a clear expression. A big smile and visible features give the model the most to exaggerate; heavy shadow or a tiny, blurry face give it less to work with.
Both. Ask for lively digital colour or a black-and-white ink style in the prompt and the model matches it. If the first result is not the look you pictured, adjust the wording and run it again for free.
New accounts start with free credits, so the first few runs cost nothing. After that the price depends on the resolution and how many images you ask for, and the estimate updates on screen before you press generate. A failed run is refunded automatically (unless it broke the content policy).
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. |
Other art styles for the same photo, and the model behind the edit.
The head grows, the features stretch, and your friends still know who it is. That is the part worth checking first.
A real edit made with this tool — drag your own photo in on the left, the prompt is already written, then press Generate.
