@laodaozzz · X

我也做了一个教小朋友学数学的工具叫easymath。

@Berbir12 · X

Dense reading shouldn’t stop your momentum. Highlight the passage that isn’t clicking. Strang turns it into a short visual explanation, right inside your browser. One complete video is free.

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。

visuali · HN

Like Claude Code for Images

AI Image Description Generator — 精准提取图片中的主要元素，解读图片创作目的；可用于科研、艺术创作中图文互搜领域

ansheng_hu · Product Hunt

MomentSift Cull, enhance, and create better photos with AI

@vkuoo · X

Added more demos showcasing graph-math relationships, built with Codex.

AI-NanoBanana — AI 图像工作室，让你轻松把创意变成高质量视觉作品

@wyfcoder · X

最近做了一个 AI 修图网站：Picuro Photo Editor。 不用复杂参数，上传图片后，直接说出你想修成的样子，比如“更清晰”“电影质感”“日系清新”“蓝天白云”，AI 就会帮你生成效果。 目前还在早期版本，欢迎试用，也欢迎提建议 🙌

chenglong-hn · HN

Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple

PicText - 图片文字编辑器 — AI 驱动的图片文本编辑器，检测并替换照片、截图和产品图中的文本，同时保留原始布局和字体

Nano Banana AI 图像编辑器 — 基于最先进的 AI 图像编辑模型 Nano Banana 开发的图片编辑器，用嘴改图、保持角色一致性、控制细节、图片融合