Diffusion PDF – A Diffusion Image Model Embedded Entirely in a PDF File
Hey Hacker News! I'm Alex, I'm 19 and I work at Hack Club! The last two weeks i've been messing around with pdfs. I made slop pdf (https://slop.alexvd.dev -- notice the similar website design), a pdf that generates random ai slop stories when you open it, and I was showing that off to one of my friends who suggested I get the LLM to actually work inside the pdf, without an API call to a relay. I laughed at the idea, but then we did some research together, and we managed to find EvanZhouDev's llm.pdf (https://github.com/EvanZhouDev/llm.pdf). Because it existed, I…
What it does
A PDF with a 55-million-parameter denoising diffusion model embedded within it.
The last two weeks i've been messing around with pdfs. I made slop pdf , a pdf that generates random ai slop stories when you open it, and I was showing that off to one of my friends who suggested I get the LLM to actually work inside the pdf, without an API call to a relay. I laughed at the idea, but then we did some research together, and we managed to find EvanZhouDev's llm.pdf . Because it existed, I didn't want to waste my time or my tokens building something like it. So I pivoted, eventually deciding to make a diffusion image model work fully inside a pdf. I forked EvanZhouDev's llm.pdf repo, and eventually managed to get it working (with the help of claude). Here's the finished…from diffusion.alexvd.dev
In the maker’s words, at launch
Hey Hacker News! I'm Alex, I'm 19 and I work at Hack Club! The last two weeks i've been messing around with pdfs. I made slop pdf (https://slop.alexvd.dev -- notice the similar website design), a pdf that generates random ai slop stories when you open it, and I was showing that off to one of my friends who suggested I get the LLM to actually work inside the pdf, without an API call to a relay. I laughed at the idea, but then we did some research together, and we managed to find EvanZhouDev's llm.pdf (https://github.com/EvanZhouDev/llm.pdf). Because it existed, I didn't want to waste my time or my tokens building something like it. So I pivoted, eventually deciding to make a diffusion image model work fully inside a pdf. I forked EvanZhouDev's llm.pdf repo, and eventually managed to get it working (with the help of claude). Here's the finished version. It took a while to train, but was worth it so i can show it to my future classmates (I'm an incoming freshman in college this year).
Does the same job
all alternatives →
- TAThePDFApi, a Chrome Based PDF Generation API Hosted on AWS2018 · ▲41
Hello HN! It kept surprising me how much of a hassle it is to generate a PDF with decent HTML5 rendering from my SaaS apps. I tried several free libs and APIs but ended up with botched rendering a lot of times. So I set out to simplify this chore by creating an AWS hosted HTML to PDF conversion API that's based on Chrome. This API will allow a dev to just send the HTML to our API and get a PDF in response without having to worry about running and managing Chrome somewhere in their infra. I just finished the first version of my landing page and hosted pdf generation API…
- TJThe Journal of AI Slop – an AI peer-review journal for AI "research"Dec 2025 · journalofaislop.com · ▲5
What it is: A fully functional academic journal where every paper must be co-authored by an LLM, and peer review is conducted by a rotating panel of 5 LLMs (Claude, Grok, GPT-4o, Gemini, Llama). If 3+ vote "publish," it's published. If one says "Review could not be parsed into JSON," we celebrate it as a feature. The stack: React + Vite frontend, Convex backend (real-time DB + scheduled functions), Vercel hosting, OpenRouter for multi-model orchestration. Each review costs ~$0.03 and takes 4-8 seconds. Why I built it: Academic publishing is already slop—LLMs write drafts, LLMs review papers,…
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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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