wowprompt

Gemini vs ChatGPT photo edit comparison blog thumbnail

A bold 16:9 blog thumbnail for a comparison of two AI photo editors: a creator holding up a phone that shows two edits of the same portrait, on a split two-colour background with a short title. Swap the words for your own article. Works with your own photo.

A young man holding up a phone showing two edits of the same portrait on a split teal and violet background, beside the words GEMINI VS CHATGPT
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

Words

Set exactly these words and nothing else. Spell each line exactly.

  • "GEMINI VS CHATGPT"
  • "FOR PHOTO EDITS"

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.

Figure

Waist-up on the right of the frame, torso square to the camera, shoulders relaxed. His right hand holds a phone upright at chest height with the screen turned to the camera; the screen shows the same woman's portrait twice, stacked top and bottom, one softer and one crisper, with no interface text. His left index finger points at the screen. Head tilted to his right, one eyebrow raised, a curious half smile, eyes on the camera.

Outfit

A white heavyweight cotton tee under an open light-wash denim shirt, a thin silver chain.

Lettering

"GEMINI VS CHATGPT" in heavy white condensed sans serif capitals with a thin black outline, two lines, very large, on the left. "FOR PHOTO EDITS" below it in black capitals on a solid white tag.

Composition

16:9. The background is split down the middle into a flat cool teal on the left and a flat deep violet on the right. He fills the right 45 per cent across the split; the text sits on the teal. Text never covers his face or the phone.

Rendering

85mm at f/2.8, a crisp soft key from the front left, a cool rim light behind him, natural true-to-life skin, real skin texture, punchy clean colour, readable at phone size.

Negative prompt

misspelled text, extra words, app logos, interface text, small text, text over face, airbrushed skin, plastic skin, waxy face, changed face, orange cast, distorted hands, extra fingers, watermark

blog thumbnailgemini vs chatgptai photo editingcomparison thumbnailfeatured imagetech blog 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