Phota in Doppelshot
Phota builds an identity profile of a person from a handful of photos, in minutes instead of a training run. Doppelshot uses it for the Studio twin: the best likeness short of training your own weights, rendered by GPT Image or Nano Banana.
What it is
- An identity profile, not a model file: Phota reads your selfies and keeps what makes your face yours.
- Rendering goes through a photo engine (GPT Image Flare or Sunburst, Nano Banana), so the look is that engine's.
- Ready in a few minutes, no 25-minute training.
What Doppelshot makes with it
- The Studio twin tier: 100 credits once, then 2 to 3 credits a photo.
- Every twin pack and your own prompt, on the twin instead of a selfie.
Engines and prices
| Engine | Kind | Price | Cards |
|---|---|---|---|
| Twin Photo (Phota, Nano Banana 2) | Twin photo | 2 credits | Just a picture, Studio headshot, Try on +18 |
| Twin Photo (Phota, GPT Flare) | Twin photo | 3 credits | Just a picture, Studio headshot, Try on +18 |
| Twin Photo (Phota, GPT Sunburst) | Twin photo | 3 credits | Just a picture, Studio headshot, Try on +18 |
Checked against the catalog on 2026-10-21.
Cards that run on it
Open a card, drop your selfie, and pick this engine in the Studio when it is not the default.

new1 free
top1 free
3 credits
2 credits
1 free
1 credit
1 free
2 creditsQuestions
Studio twin or Trained twin?
Studio (Phota) is faster and gives the best likeness for most people. Trained gives you your own weights to download, trained on Ideogram.
How many selfies?
Ten to twenty clear photos of your face, different days and lights. The app checks them and tells you which to replace.
Try it on your selfieThe first preview is free, no card needed.
Other models
from 1 creditsIdeogramby IdeogramTypography that reads: posters, covers and any image with exact text. Twin training too.from 1 creditsFLUXby Black Forest LabsBlack Forest Labs: FLUX.3 photos, FLUX Fill for one-zone edits.from 1 creditsNano Bananaby GoogleGoogle's image models: fast, faithful to your face, up to 4K with Pro.from 1 creditsGPT Imageby OpenAIOpenAI's image model: rich scenes, strong styles, readable text.