Feed aggregator

Show HN: Diffulab, a library to train diffusion models from scratch

Hacker News - Sat, 04/26/2025 - 9:48am

Lately a friend of mine has been working on a personal project and I wanted to share it. The goal of Diffulab is to provide a flexible and modular framework for training diffusion models from scratch. The project is still in its early stages, and he is actively working on adding new features and improvements.

Comments URL: https://news.ycombinator.com/item?id=43803593

Points: 7

# Comments: 0

Categories: Hacker News

Premier League Soccer: Stream Newcastle vs. Ipswich Live From Anywhere

CNET Feed - Sat, 04/26/2025 - 9:32am
Clash at St. James' Park has significant implications for both ends of the table.​
Categories: CNET

Copa del Rey Final: How to Watch Barcelona vs. Real Madrid Soccer Livestream From Anywhere

CNET Feed - Sat, 04/26/2025 - 9:00am
It's an El Clasico final at the Estadio La Cartuja in Seville on Saturday.
Categories: CNET

Hulu's Finest: 21 of the Best TV Shows to Stream Right Now

CNET Feed - Sat, 04/26/2025 - 9:00am
Go beyond Grey's Anatomy and Abbott Elementary on the streamer.
Categories: CNET

Show HN: My self-written hobby OS is finally running on my vintage IBM ThinkPad

Hacker News - Sat, 04/26/2025 - 8:51am

Finally got my hobby OS up and running on real hardware. I love the old IBM thinkpads, so thought it was the perfect machine to get it working on. Been working on it for quite some time now, but this has been a big milestone!

Comments URL: https://news.ycombinator.com/item?id=43803148

Points: 2

# Comments: 1

Categories: Hacker News

Show HN: Gemini Document Processor – Generate Th Summaries from PDF/ePub with AI

Hacker News - Sat, 04/26/2025 - 8:50am

Hello HN! I'd like to share Gemini Document Processor, an open-source tool I've developed.

This tool uses Google's Gemini AI (their latest API) to create high-quality Thai language summaries from PDF and EPUB files. Key features include:

- Support for both PDF and EPUB files - Intelligent chunking for efficient Gemini API processing - Automatic image extraction from documents - Direct integration with Obsidian (export directly to vault) - Smart retry system when errors occur (switches models/increases timeouts) - Real-time progress tracking via web interface

I built this tool because I needed to read many English documents and wanted detailed summaries in Thai.

If you frequently read long documents or want to build a knowledge base from multiple sources, this tool could save you significant time.

The output is a well-formatted Markdown file with images and metadata, ideal for storing in Obsidian, Notion, or other PKM systems.

Try it by cloning the repo and running it with Python (requires a Google Gemini API key).

Feedback, suggestions, and contributions are very welcome!

Comments URL: https://news.ycombinator.com/item?id=43803143

Points: 1

# Comments: 0

Categories: Hacker News

Pages