News for hackers. Stuff that matters.

wushi

Recently came across this project. Artificial Analysis currently lists HappyHorse-1.0 at #1 on the Text-to-Video (No Audio) leaderboard, and their Image-to-Video page also indicates it leads there as well.

The leaderboard ranking is from Artificial Analysis; the architecture details on the site are from the project’s own public materials.

Interesting mainly because it seems to combine strong blind-preference results with a fairly ambitious public technical story around a unified multimodal video model.

HappyHorse-1.0: an open video model now ranked #1 on Artificial Analysis

Recently came across this project. Artificial Analysis currently lists HappyHorse-1.0 at #1 on the Text-to-Video (No Audio) leaderboard, and their Image-to-Video page also indicates it leads there as well.The leaderboard ranking is from Artificial Analysis; the architecture details on the site are from the project’s own public materials.Interesting mainly because it seems to combine strong...

( Read More... | 3 comments | on HN )

Show HN: Sora2 watermark is heavy, so I built a one-click remover

https://sorawatermarkremover.net

Since Sora’s second-gen video tool, the corner watermark has become noticeably harder to deal with. When distributing clips to other platforms—especially for vertical edits, mashups, or remixes—it looks out of place. I often need a clean version for editing and packaging, so I built a simple button: upload → click → download. Site: sorawatermarkremover.netWhat it doesAutomatically detects the...

( Read More... | 1 comment | 2 points | on HN )

Show HN: Built FLUX.1 Kontext image editor – context-aware AI editing

https://flux1kontext.io

Hey HN,I've been working on https://flux1kontext.io – an AI image editor that uses Black Forest Labs' FLUX.1 Kontext models for context-aware image editing.*What it does:* Upload an image, describe what you want to change, and it modifies just that part while keeping everything else intact. Think "add sunglasses to this person" or "make the cat open its eyes" – it understands context instead of...

( Read More... | 1 comment | on HN )

Show HN: Tidyread, an ADHD-Friendly RSS Reader, Powered by AI

https://tidyread.ai

Living with ADHD, I often get easily distracted. I find myself frustrated with certain algorithmic recommendations that seem to exploit my vulnerabilities. These algorithms trigger FOMO or cater to my impulses, leaving me feeling out of control and overwhelmed.I once thought RSS readers could solve my problem, but I still faced new issues that made me want to escape:1. Many sources only provide...

( Read More... | no comments | 3 points | on HN )
This tool sounds great for info overload like me. Algorithmic recommendations always make me feel helpless, hope this tool can help me regain control.