I built an AI tool that generates click-worthy YouTube thumbnails
Hey HN! Software engineer here. As an amateur youtuber, I've been struggling with thumbnails, especially since I don't have any design or editing skills. Decided to give it a try and make my own automatic thumbnail generator. Me being an ADHD person, made sure that there's no parameter tuning and shape choosing and fuss like that, just simply give prompt and generate thumbnail. Increased my CTR from 1.2% to 2.3% (faceless fantasy books niche on youtube) Thumbnail X (completely free for now) - https://thumbnailx.com/ Just wanna add that this is by no means a perfect thumbnail…
What it does
In the maker’s words, at launch
Hey HN! Software engineer here. As an amateur youtuber, I've been struggling with thumbnails, especially since I don't have any design or editing skills. Decided to give it a try and make my own automatic thumbnail generator. Me being an ADHD person, made sure that there's no parameter tuning and shape choosing and fuss like that, just simply give prompt and generate thumbnail. Increased my CTR from 1.2% to 2.3% (faceless fantasy books niche on youtube) Thumbnail X (completely free for now) - https://thumbnailx.com/ Just wanna add that this is by no means a perfect thumbnail maker for huge YouTube moguls with millions of subscribers but I'm sure it's gonna be extremely helpful for beginner youtubers and medium size channels struggling with thumbnails. Tools used: 1. Cursor for development (shoutout to claude oppus 4.0) 2. Few image generators (primarily ideogram, but leonardo ai, deep ai and gpt 4o as fallbacks) 3. Few llms (chatgpt, claude, gemini for validating images and prompt enhancement) 4. AWS and Redis for storage & caching 5. Digital ocean for hosting and db 6. Python
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
