wowprompt

I tried 5 AI photo trends thumbnail with before and after frames

A bold 16:9 YouTube thumbnail for an AI photo trends video: a creator with a wide-eyed surprised face on the right, two small before-and-after photo frames on the left and a big two-line title. Swap the words for your own video. Works with your own photo.

A young man in a mustard overshirt with a surprised open-mouth face beside two small photo frames of the same man, one plain and one in black and white
The output this prompt produced, unedited.
Works with or without your photo.

Optional. Attach a clear, front-facing photo to keep your own face. Without one, the prompt creates an original person.

The prompt

Text

  • "I TRIED 5"
  • "AI PHOTO TRENDS"
  • "BEFORE"
  • "AFTER"

Set exactly these four lines and nothing else. Spell each line exactly.

Identity

With a photo attached: the person in the photo is the subject. Keep their face exactly as it is, with bone structure, eye shape and spacing, nose, lips, jawline, hairline, skin tone and apparent age all unchanged, and keep their own body: build, height and proportions, shoulders, arms, hands and legs, with the same skin tone on face, neck, arms and hands. Use the photo only for who the person is. Ignore its pose, expression, clothing, hairstyle, background, framing and light, and rebuild all of them exactly as described below, even when the photo shows them standing straight or dressed differently.

Type

"I TRIED 5" in heavy white condensed sans serif capitals with a thin black outline, across the top left. "AI PHOTO TRENDS" below it, larger, in black capitals on a solid bright lime-green band. "BEFORE" and "AFTER" as tiny white capitals on small black tags at the bottom of each frame.

Layout

The subject fills the right 45 per cent, framed from the chest up, torso square to the camera, head pushed slightly forward. His right hand is raised beside his face, palm open toward the camera; his left hand is out of frame. Eyebrows high, eyes wide, mouth open in a surprised O, looking at the camera. Below the title on the left, two small tilted photo frames with white borders sit side by side: the left one shows a plain, flat phone selfie of him, the right one the same face as a dramatic black and white rim-lit portrait.

Image

He wears a mustard corduroy overshirt open over a plain white tee. Behind him a softly blurred deep teal wall. 50mm at f/2.8, a crisp cool key from the front left, a thin white rim on his right side, natural true-to-life colour, real skin texture, punchy clean contrast, readable at phone size.

Negative prompt

misspelled text, extra words, small text, text over face, cluttered layout, cartoon face, orange cast, airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, logo, watermark

youtube thumbnailai photo trendsbefore and after thumbnailai photo editing videosurprised face thumbnailcreator thumbnail

How to run this

Copy the prompt and paste it into GPT Image, then set the aspect ratio to 16:9. Upload your reference photo before pasting, not after: a model that has already started without it will invent a face instead of keeping yours.

The prompt is written in Markdown with each part under its own heading, which is what the copy action hands over. Change one section at a time, keeping the rest intact, so you can tell which change did the work.

Related prompts

All productivity