What the tech

Search

/ opens search from anywhere. Esc closes it.

Tools

Get the newsletter
Example result of this prompt The made-up input photo InputExample result

Example Example made on our own Mac with open models (Z-Image and FLUX.2 klein). Your result in the AI above will look different. How we make examples

YouTube thumbnail with your face and a title

A bold, clickable video thumbnail with your face, a clear expression and a short title. You need one photo of yourself.

You need
1 photo of yours
Written for
Gemini, ChatGPT, Ideogram
Result
Image

Prompt

Make a 16:9 video thumbnail using my photo. Put me on the side third of the frame, from the chest up, with a expression expression, sharply cut out with a subtle white outline. Keep my face, identity and proportions exactly as in the photo. On the other side, add the title "title" in huge, bold, high-contrast letters with a thin dark outline, spelled exactly as written, at most two lines. Behind everything, a bright, simple background about topic with strong colors and slight blur. Easy to read at small sizes. No logos, no platform icons, no other text.

Fill in, or keep the brackets and change them later

side
expression
title
topic

How to use it

  1. Take a well-lit photo of yourself making the expression you want.
  2. Open ChatGPT or Gemini, attach the photo and paste the prompt with your title.
  3. Shrink the result on your phone; if you cannot read the title at that size, shorten it.
What to expectYour face can change a little, especially when the AI changes your expression, and the title may be misspelled, so check both.

Tips

  • Three to five words is the sweet spot for a thumbnail title.
  • A real expression in your photo beats one the AI invents.
  • Keep the bottom-right corner clear; the video length covers it.

Editor: Peyman Khosravani · Updated November 18, 2026