pixsprout.com — 专注于生成复古橡皮印章效果的 AI 工具，支持文字生成印章、图片转印章及自动去底 - [更多介绍](https://pixsprout.com/image-to-stamp)

aniv — 一站式 AI 创作工具站，浏览器打开即用：AI 文生图、AI 文生视频、视频画质增强、字幕合成

@jitendraballa · X

PromptArk — 帮助用户优化提示词，用户输入简单的提示词，AI 辅助生成更结构化，更详细的提示词

@Akinzoooo · X

Free Qwen Image Edit AI — Qwen Image Edit 网站。高级 AI 图像编辑与完美文本渲染，完美支持中英文文本渲染。

GPT Image 2 — AI 图片生成器，支持文生图、图生图、4K 图片、图中文字生成与 Prompt 示例库，适合制作产品图、海报、广告图和社媒配图

AI 工作流模板生成器 — 免费 AI 工作流生成工具，输入重复任务、角色和输出格式，自动生成任务边界、处理步骤、提示词和质检清单。

@listudio · X

Fable 5 规划+Codex 执行，效率真的很 ok。一个周末上线了两个工具网站。麻了。。 👉： 和

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

@AshiveCompany · X

@appsbywill · X

i've been playing around with this profile picture maker, I really want to fine tune the background removal and add more styling templates. Let me know if you find more bugs!