wowprompt

New city vlog thumbnail seen from below a rooftop railing at sunset

A wide vlog thumbnail shot from slightly below: a young man leaning on a rooftop railing with the skyline glowing behind him and three big words on the open sky. Made for a moving-out, first-week or city-diary video. Works with your own photo.

A young man leaning on a rooftop railing at sunset seen from slightly below, the city skyline blurred behind him and NEW CITY DAY 1 on the sky
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

Must hold

One person only. The words are exactly those below, large enough to read on a phone, and never across his face. He stays on the right third; the sky on the left is kept clear for the type.

Text

  • "NEW CITY"
  • "DAY 1"

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. Only the clothing, pose, setting and light come from this prompt.

The picture

He leans on a steel and glass rooftop railing, relaxed, one hand in his pocket, looking out over the city with the start of a smile. The camera sits a little below him, so the railing crosses the lower frame and open sky fills the space above. He wears an olive cotton overshirt over a white T-shirt, black jeans and a canvas backpack on one shoulder. Towers and water tanks fade into warm haze behind. "NEW CITY" sits on the sky at upper left in heavy white capitals, with "DAY 1" below it in amber.

Technical

Low golden sun from behind as a rim, warm bounce on the face, the skyline in bokeh. A 135mm lens at f/2, the background compressed into soft colour. A restrained teal and orange grade, skin kept natural with pores.

Negative prompt

misspelled text, extra words, extra glyphs, small unreadable text, text over the face, arrows, emoji, harsh noon sun, flat lighting, airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, logo, watermark

youtube thumbnailvlog thumbnailrooftop sunsetcity skylinemens portraitmoving vlog

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