One photo in · A cinematic one-sheet out · Free to start
The hero pose, the dramatic light, the storm-lit city and the title treatment. It is a cinematic one-sheet with you as the lead, from one photo.
A real one-sheet, generated by the model behind this page. Drag the divider to compare the plain studio portrait with the finished key art. Every output is AI-generated, so your result varies with your photo, your prompt, and the genre you describe — treat this as a preview of what the tool can do, not a fixed result.


Drag to compare before and after
The low-angle hero stance, the hard rim light, the rain-soaked neon street, the teal-and-orange grade, the title treatment burned across the lower third — the kind of theatrical one-sheet a studio would commission from a key-art agency, built from one ordinary photo.
Instead of hiring a photographer, a retoucher and a designer for a single image, you upload a clear picture, name the genre you want, and the model builds the whole composition while keeping your face and expression recognisable. The point of starting from your own photo is that the result still reads as you on the billing block, not a stranger who happens to share your jacket.
On Kavel the tool runs on the Nano Banana image model, so a finished one-sheet comes back in one generation rather than an afternoon of compositing and type-setting. You start from your uploaded picture — 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 genre costs nothing but time.
It suits someone making a birthday or leaving gift, a creator building a striking profile image, a band or a team wanting key art for an announcement, or anyone who simply wants to see themselves headlining something. The title and credits it invents are fictional by design — this makes an original piece of key art around you, not a copy of an existing film.
And because the same studio also changes hair, swaps outfits and handles other photo edits, one workflow covers a range of looks without a new tool for each.
Creative engine
Upload a photo, name the genre, choose the format and resolution, and the credit estimate updates before you generate.
Upload one clear photo and the model reads your face, then rebuilds the shot as a full theatrical one-sheet around it.
Name the genre and the mood — neon thriller, epic drama, horror, indie — and the key art follows that brief.
Set the format, check the credit estimate, and generate; a failed run is refunded (unless it broke the content policy), so a second genre is free to try. A movie poster is the loudest way to print a face. The Polaroid is the quietest, and the 90s yearbook portrait sits between the two.
From one plain photo to finished key art, with the cost shown before you commit.
Add one clear picture with your face visible and evenly lit. A sharp, front-facing shot with room around your shoulders gives the model the most to build a composition from and the best chance of holding your likeness.
Set the brief: a neon-noir thriller in the rain, a sun-bleached western, a cold sci-fi epic, a title treatment across the bottom. Specific direction keeps the key art on-genre instead of generic.
Confirm the estimate, generate the artwork, and download it to share or print. If a run fails, it is free, so you can adjust the brief and try another genre.
Film-school projects, gag gifts, launch posts that want a title treatment.
Turn a colleague's photo into a leaving-gift one-sheet, or a friend's into a birthday print — the kind of joke that lands because the face is unmistakably theirs.
Build a scroll-stopping banner or profile image in minutes rather than briefing a designer and waiting on rounds of key art.
Give a band, a club, or a launch its own theatrical artwork — same treatment for every member, generated from the photos you already have.
Common questions about casting yourself in cinematic key art with Kavel.
The staging and the styling. You end up in a hero pose under hard rim light, with a dramatic background, a cinematic grade, and a title treatment across the lower third — while your face and expression carry over from the photo you started with. Nothing about your identity is invented; it is restaged, not replaced.
No, and that is deliberate. The model invents a fictional title and a placeholder billing block so the result is original key art built around you, rather than a copy of an existing film. If you want a specific title on it, name that title in your prompt and it will be set into the artwork instead. Text in generated images can occasionally come out uneven, so if a letter looks off, generate again or keep the title short.
A sharp, front-facing shot with your face evenly lit and a little space around your shoulders. Everything else — the pose, the light, the city behind you — is being built around you, so the face is the only part that has to survive intact. A dim or blurry original gives the model less to hold onto.
Yes. Describe it and the artwork follows — a neon thriller in the rain, a cold sci-fi epic, a warm indie drama, a horror one-sheet with a single light source. A clearer, more specific brief gives a closer result than a vague one, so it helps to name the mood, the palette, and the setting rather than leaving them to chance. If the first pass is close but not quite there, adjust one detail at a time and generate again.
It depends on the resolution you pick and how many versions you generate, and the estimate is on screen before you press the button, so there is no surprise afterwards. Free credits arrive with the account, and a failed run is refunded automatically (unless it broke the content policy). Because a failed run is refunded, you can keep trying genres — thriller, epic, horror — until the artwork looks right, without watching a meter tick up on every attempt.
Yes. Generate at a higher resolution before downloading if it is going to a printer — a 1K file will look fine on a phone but will not survive being printed at one-sheet size. For a framed gift, pick the largest resolution the estimate offers, then download the file and send it to your printer as usual; the higher the resolution, the more the title type and the fine detail hold up at scale.
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. |
Name a genre and the one-sheet builds itself around your face — lighting, title treatment and all. Swap the genre and the whole poster re-shoots.