@buildlylibrary · X

mistakevin · HN

I've been working on https://notebooker.ai if anyone is interested in giving some feedback. I tried to post a Show HN yesterday with details about how I built it, but was auto-flagged and not sure what rules I broke. Everything that I've built on top of open-notebook, like the plugin system for your own "creators" (aka, podcasts, infographics, etc) is at https://github.com/Notebooker-ai plus a Cloudflare Worker AI deployer to play with different models. Been working on it for about six months.

Midjourney Sref code 精选库 — 在 Midjourney 的 prompt 输入 `--sref xxx` ，可以固定生成某种特定风格的图片。这对很多人来说非常方便，不用写一堆效果词，只要记住几位数字就可以。但 `--sref xxx` 有大概 40 亿个，其中重复或者质量不佳的不在少数。因此做了一个网站把一些个人觉得不错的 sref code 收集起来并进行分类，方便新人或

victords · HN

I was interested in learning more about reverse image search, so I built audioguide.london. It’s a simple image search where you take a photo of an artwork in a gallery, tries to ID it and returns a pre-generated audio and a link to the museum website. The audios were all generated locally, essentially looking at the contents of the website, running it through a LLM to generate a script and Kokoro for TTS. I’ve built it as an app for myself almost a year ago, so I deployed it as a vibe coded web

@polyqoy · X

This video shows a fully animated 3D site built in 2 minutes with claude code. one terminal command. but the prompt was almost irrelevant. the real work was the pre-load: ui/ux pro max skill, a hero component from framer motion stacked in before claude touched anything the toolkit did the job. the prompt just pulled the trigger. that's also why most people's claude output looks generic. they skip the setup and blame the model.

@aviralgarg05 · X

Here's what you get on One toolkit. Every design task.