One photo in · Pro shot out · Free to try, no sign-up
Pick a scene and a light, keep your own face, and have the polished shot back in under a minute.
A real polished portrait, rendered on this page’s model. Drag the divider to compare the original snapshot with the upgraded shot. Every output is AI-generated, so your finished picture varies with your photo, your prompt, and the scene 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
A dim mirror shot and a good portrait differ mostly in light, and light is the one thing you cannot go back and fix by hand. You upload a clear picture, describe the scene and lighting you want, and the model restyles the light, colour, and background while keeping your face and pose recognizable — no photographer, no studio.
On Kavel the tool runs on the Nano Banana image model, so an upgraded shot finishes in one generation rather than a manual retouch.
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 scene costs nothing but time. The result suits someone refreshing a profile picture, a creator who needs a clean headshot fast, or anyone who wants a favourite snapshot to look its best.
And because the same studio also changes the hair and the outfit in that same portrait, one workflow covers a whole camera roll of ideas without a new tool for each. Think of it less as a filter and more as a fast portrait booth — with the styling in your hands, and your own face in the frame.
Creative engine
Upload a photo, describe the scene and light, choose the format and resolution, and the credit estimate updates before you generate.
Upload one snapshot and the model reads your face, then upgrades the light, colour, and background into a cleaner shot.
Describe the scene you want — a sunset street, a studio backdrop, soft window light — and the edit follows that brief.
Set the format, check the credit estimate, and generate; a run that fails costs you nothing, so a second scene is free to try. A selfie is a pose and an angle decided together. To control them separately, the pose changer handles the stance and the camera angle changer handles the viewpoint.
From one snapshot to a polished shot, with the cost shown before you commit.
Add one clear photo with your face visible. Even a plain snapshot works — the model has more to build on when the face is sharp and lit.
Set the mood: golden-hour street, clean studio, soft indoor light, a colour grade. Naming the light — golden hour, soft studio — steers the whole shot.
Confirm the estimate, generate the shot, and download it. If a run fails, it is free, so you can adjust and try another scene.
Dating profiles, LinkedIn headers, anyone who hates their camera roll.
Turn an ordinary snapshot into a flattering shot for your profile, and put your best face forward without a new shoot.
Get a clean, well-lit headshot fast for a bio, a resume, or a channel, without booking a photographer.
Give a favourite photo the light it deserves — a trip, a night out, a candid moment — so it finally looks its best.
Common questions about turning a photo into a polished shot with Kavel.
The light, the background, and the colour grade — not you. A flat indoor snapshot becomes a shot that looks like it was taken outdoors at the right hour with a fast lens: warm backlight, a softly blurred background, and a proper grade over the top. Your face, hair, and pose stay as they were.
Yes. Free credits arrive with the account, and a generation that fails is refunded automatically (unless it broke the content policy). Beyond that, cost depends on the resolution and the number of images, and the estimate appears before you commit.
No — a phone shot is the normal input. What matters is that your face is sharp and not badly underexposed. The tool can rebuild the light around you, but it cannot invent detail that the sensor never captured.
Yes, and you should. Golden-hour street, overcast studio, neon at night, a blurred cafe — naming the scene and the light is the difference between a generic polish and a shot that looks deliberate.
That is the constraint the model works under: keep the same face, hair, and pose. If a result drifts too far, say so explicitly in the prompt and run it again. If it still drifts, start from a sharper photo — soft input is the usual cause.
That is what most people do with it. Generate at a higher resolution if the platform crops hard, and keep the framing tight enough that a square crop does not cut your head off.
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. |
The engine behind the portrait, and other ways to upgrade the same shot.
Name the scene and the light, and the shot comes back with your face still yours. If the mood is off, the next scene is one sentence away.
A real edit made with this tool — drag your own photo in on the left, the prompt is already written, then press Generate.
