wowprompt

I tried 7 AI photo trends YouTube thumbnail with a portrait grid

A YouTube thumbnail for a video trying popular AI photo styles: a young man on the left points with an amazed grin at a neat grid of seven small portraits of himself, each in a clearly different style from black and white to anime to clay figurine, with a big bold headline. Works with your own photo.

A young man pointing with an amazed grin at a grid of seven small portraits of himself in different styles, beside the words I TRIED 7 AI PHOTO TRENDS
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

The commission

A thumbnail that sells curiosity in half a second: one real, delighted face and seven tiny versions of that same face in seven unmistakably different styles, with one short headline.

Text

  • "I TRIED 7"
  • "AI PHOTO TRENDS"

Nothing else is written anywhere. Spell each line exactly. The small portraits carry no captions or numbers.

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. The same face appears in all seven small portraits.

In frame

He fills the left third, chest up, torso turned toward the grid on the right, head turned back to the lens, eyebrows high, mouth open in an amazed grin. His right arm stretches across his body, index finger pointing at the grid; his left hand rests flat on his chest.

Wardrobe

A plain cobalt-blue crewneck tee, a thin black cord bracelet, short neat sides on his hair.

The set

On the right two thirds, a clean grid of seven square tiles on a deep navy background, four on top and three below, each with a thin white border, all showing his face: a true black and white studio portrait, a flat 2D anime cel, a 1990s studio portrait with a painted backdrop, a glossy 3D toy figurine, an oil painting, a double exposure with a city skyline, a rainy night street with neon reflections. "I TRIED 7" in heavy white condensed capitals above the grid, "AI PHOTO TRENDS" below in black capitals on a bright yellow bar.

The light and how it is shot

A crisp cool front key and a white rim on his shoulders. 35mm at f/4, eye level. Natural true-to-life colour on him, real skin with pores, clean contrast for a small screen.

Negative prompt

misspelled text, extra words, captions under tiles, numbers on tiles, app logos, real brand logos, licensed characters, different faces in the tiles, orange cast, warm grade, airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, watermark

ai photo trends thumbnaili tried ai trends videoai photo editing youtube thumbnailai portrait stylesyoutube thumbnail with gridtech youtube 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