AI Thumbnail Generator with Real Photos

O que você precisa

• A real photo of yourself (pointing at something works best for the default mode)

• Claude Code, or another AI tool such as Claude Cowork, ChatGPT or Codex

• A Mac or Windows computer (the AI installs Python and the other dependencies)

Passo a passo

1. 1

   Start from a real photo of you

   0:29

   Take or pick a photo of yourself. The tool never generates images: every pixel in the thumbnail is your photo or text drawn on it. If you want text or a logo to appear in your hand, point your finger where it should go.

2. 2

   Know what the tool does with it

   0:34

   MediaPipe detects where your face points and where your index fingertip is. IS-Net (through rembg) cuts you out of the image, which gives the depth effect. Then the text or logo is placed either where you point or right behind you, depending on the mode.

3. 3

   Understand the readability loop

   1:11

   Thumbnails are shown very small, so the tool checks whether the text contrast is good enough for people to read. If it is not, it keeps looping (moving the text and trying again) until it gets a readable result.

4. 4

   Open your AI coding tool

   1:37

   Open Claude Code. You can also use Claude Cowork, ChatGPT or Codex: in my experience, any of them works.

5. 5

   Paste the prompt

   1:50

   Paste the improved prompt from the description. It builds the system with both modes at once: text beside you, or poster-scale text behind you.

   Prompt from the videoCopiar

   Build a local Python tool: one photo → a 1280×720 thumbnail, no image generation: every pixel is the photo or type drawn on it. MediaPipe for the face and the index-fingertip direction, rembg isnet-general-use for the cutout. Render through Playwright and take every measurement from that same page, so the glyph mask you score is the file you ship.
   
   Place type by scoring the real pixels under the glyphs with APCA (display type at feed size needs Lc 45–60, not 75). Try several positions, keep one where 90% of the text area passes, pick dark or white, scrim only if neither works bare. Multiply the mask by 1 − subject alpha so hidden letters don't count as text.
   
   Two modes. Default: type avoids the person. Carve each candidate box down to its subject-free space first or the autofit grows the headline across them, and check letters individually, since one can be swallowed while the total still reads 90%. Backdrop: type is the set: poster scale, two-thirds of the frame, person in front. Interruption is the point, so drop the per-letter test; let me nominate a must-read phrase instead, inked on its own span so it's measured separately. No scrim. Place a logo by measurement, growing its mask first so near-misses count as crowded.
   
   Then shrink to 168px and re-measure. If it stops being readable, move the text and try again.
   
   MediaPipe 1.0 dropped mp.solutions: Tasks API, Python 3.12.

6. 6

   Let it build and install everything

   2:21

   Let the AI write the code and install the dependencies it needs, such as Python. This works whether you are on a Mac or on Windows.

7. 7

   Run a test on your own photo

   2:40

   Ask it to run a test using a photo that is already on your computer. Check the thumbnail it produces, including any logo placement (my test put the Anthropic logo below my text).

8. 8

   Pick the mode for each thumbnail

   3:29

   Use the default mode when you point at something and want the text to appear there. Use the backdrop mode to cut you out and put large text behind you for the depth effect.

Assista em seguida

• 9:15How You Can Grow Your YouTube Channel with ClaudeFind which of your videos need new thumbnails by sorting them on click-through rate.
• 5:55How I'm Building an AI-Native YouTube ChannelPlan a YouTube workflow where AI helps with ideas, editing and tracking.