- Genial
- Tutorials over AI en automatisering
- Stop Using AI Images for Your Thumbnails
Stop Using AI Images for Your Thumbnails
AI can build a smart YouTube thumbnail generator without inventing a single pixel. In this video, I break down a local Python workflow that uses your real photo, detects your face and pointing direction, removes the background, and places readable typography automatically. You will see how I built and tested both thumbnail modes with Claude Code, plus the exact prompt so you can recreate the tool yourself.
⏱️ TIMESTAMPS:
0:00 Why AI-generated thumbnails look off 0:27 How the generator works 1:31 The exact prompt and Claude Code build 2:21 How AI assembled the system 2:51 Testing it on a real photo 3:21 The two thumbnail modes 3:44 Keeping your face human 3:58 Prompt recap and closing
🧩 PROMPT FROM THE VIDEO:
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.
🔗 CONNECT WITH ME:
💼 LinkedIn: https://www.linkedin.com/in/miguel-torrez/ 🌐 Genial Agency: https://genial-agency.com 🇫🇷 Luwai (French): https://luwai.fr 👤 Personal: https://migueltorrez.ai 📅 Book a chat: https://cal.com/miguel-torrez
🛠️ TOOLS MENTIONED:
• Claude: https://claude.ai • Codex: https://chatgpt.com/codex • ChatGPT: https://openai.com • MediaPipe: https://mediapipe.dev/ • rembg: https://github.com/danielgatis/rembg • Playwright: https://playwright.dev/
💬 DROP A COMMENT:
Which mode would you use first: text beside you or poster-scale text behind you?
#AI #YouTubeThumbnails #ClaudeCode #ContentCreation #Python


