

Photo retake guide
Someone blinked in the one shot that mattered? Upload it and the retake opens the eyes and keeps everything else. No reshoot, no second photo.


A blink takes a fraction of a second, and most people blink many times a minute. Every extra face in the frame is another chance that someone's eyes are shut, which is why the best moment of the day is so often the one with a blink in it.
A retake keeps the photo you took and redraws only the eyes and the expression, using the rest of the face so it still looks like you. You don't need a second photo, and you don't need to reshoot.
Hover or tap a photo to see Take 1. Each Take 2 is a real GPT Image 2.5 retake of Take 1. The people shown are AI-generated.








Name who to fix and the prompt asks for everyone else to stay as they were. Move the lens over the photo to see Take 1 underneath.

Move the lensThe prompt is written for you, and you can read it and change it in Create before anything runs.

Any photo you'd keep if it weren't for the face. It waits on your device until you continue.
Tap what's wrong. For a group photo, say who. That becomes your prompt.
Create opens with your photo attached, GPT Image 2.5 selected and the prompt filled in.
Every guide opens the same tool with the right fixes already picked.
Yes. A retake redraws the eyes and expression using the rest of your face, so the eyes are drawn to match you. It works best when the face is not tiny in the frame.
No. One photo is enough. The model uses the visible face to draw open eyes.
Yes. Type who to fix, and the prompt tells the model to leave everyone else as they were.
One retake of a standard 4:3 phone photo costs 21 credits. Other photo shapes cost 19 to 26 credits. This page shows the price for your photo before you continue, and Create shows it again before you press Generate.
Keep the moment. Fix the face.



