@mhroxy3112 · X

PicSpeak — 基于 AI 的摄影点评 Web 应用，上传一张照片，几秒钟内即可获得对构图、光线与色彩的专业分析，同时可以向社区展示你的优秀作品。

@9to5_Dad · X

Ai mobile app ui designer with taste

@damiadeh · X

Your files utility tools stacks in your browser. No uploads, files stays on your pc.

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

@iamdeepak89 · X

@jyotipathak___ · X

We launched Vault today and we’re excited to take you through an experience designed to impress from the first scroll to the last. Vault is a React/Next.js effects library. Preview the effect. Install it. Ship it. Constructive feedbacks appreciated

asm28208 · HN

AI Law Tracker – one audited API for US, EU and global AI law

plutozc · V2EX

做了个 Codex Desktop 主题预览和切换工具，先调好再安装 最近一直在用 Codex Desktop ，觉得默认界面看久了有点单调，就顺手做了个主题编辑工具，分享一下： [Codex Skin]( https://getcodexskin.com) 可以先在网页里预览主题，调整背景透明度、面板透明度、颜色、模糊和圆角等参数，满意之后再下载并切换到 Codex Desktop 。 目前支持： - 自定义 JPG 、PNG 、WebP 背景 - 在线实时预览主题效果 - 调整透明度、颜色、模糊、圆角 - 预览满意后生成安装命令 - 不喜欢了可以恢复默认外观 目前主要面向 macOS 上的 Codex Desktop ，还是个人项目，功能和兼容性都在继续打磨。 欢迎试试，也想听听大家对主题参数、预览效果和安装流程的反馈。 直接网址： https://getcodexskin.com [轻喷 轻喷，可能还有些 bug

@itz_sayan_03 · X

Ever wondered how cinematic scroll-driven websites are built? 👀 Meet SectionFlow—an open-source React library with 60+ ready-to-use section transitions, a one-command CLI, reusable sections, and optimized performance. 🚀

Sriram1729 · HN

Tampa, FL | Remote (US Eastern) | Contract, ~20 hrs/week (evenings + weekends, around a full-time job)I'm a full-stack + AI engineer, 5 years in. Looking for one side engagement I can actually commit to — nights and weekends, not a flaky "I'll get to it" thing. Short version of what I'm good for: give me a problem and I'll hand back something deployed. I do the whole thing — backend, frontend, the data model, the infra, the deploy. You don't need to spec it out for me or check my work line by li

apoorvumang · HN

TokenPath – token-level citations for LLM output, read from attention