@eskayML · X

Lead gen for dummies

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

@MBKariyawasam · X

@abrahamelo_ · X

Seedream AI — Seedream AI 4.0 AI 图片生成器（最新，免费）

@allenjones126 · X

I’m building a form builder, form backend and a lead pipeline in one tool.

@st0yanov · X

Nano Banana 2 — AI 生图工具，Nano Banana 2 是面向设计师、运营和内容创作者的在线 AI 生图工具，支持「预设工坊 + 自由创作」双模式，内置多种风格模板与 50+ 涂鸦字体，输入文字即可快速生成高质量图片；同时支持多语言文字渲染、参数可调、浏览器即开即用。最新上线的批量生图功能可一次生成多张或多版本图片，适合海报、电商素材和社媒内容的规模化生产，显著提升出图效率

@Yogeswar__ · X

Hey, I recently created a saas for Freelancers. Website : Demo-vedio: Any feedback ? Mailto : [email protected]

OtmaneBenazzou · HN

I was tired of always having to check dog safety charts and weather reports whenever I wanted to walk my dog, so I made a quick tool to know when it's safe. (Yes, this is vibe coded, so take it with a grain of salt ;))

@MrTechPM · X

Built this because I was tired of job hunting feeling like a second full-time job. JobFlow automatically tracks applications from your inbox, organises your job search, and gives AI-powered guidance throughout the process. Still early, feedback helps...

Plugcamp · V2EX

最近在折腾一个小站，主要是围绕 Nano Banana 2 Lite 做图片生成和图片编辑： https://nanobanana2lite.me/ 一开始只是自己想要一个比较轻的入口，用来快速试 prompt 。后来发现每次测图都会遇到几个重复问题： - prompt 写完之后，不知道适合什么比例 - 文生图和图生图入口经常混在一起 - 想找几个可复制的 prompt 示例，但很多站要么太重，要么示例不够直观 - 只是想快速生成一张产品图、头像、广告图、封面图，不想进一个很复杂的工作台 所以就做了这个站。 目前主要有几个部分： - Text to Image：直接输入 prompt 生成图 - Image to Image：上传一张图，再用 prompt 做改图 - AI Image Editor：偏日常编辑，比如换背景、改光线、改风格 - Prompt Library：整理了一些可直接复制的 prompt - Gallery：放了一些 before/after 和示例图 我自己比较在意的是首页别太像传统 SaaS 落地页，所以最近一直在改视觉。之前太干了，后来加了一些更丰富的样张和暗色主题，但也还在调。 这个站不是 Google 官方产品，只是一个第三方工具站。现在更多是想把「轻量、直接、可复制」这件事做好。 如果大家有空的话，想请教几个问题： 1. 首屏看起来会不会太营销，还是说信息还算清楚？ 2. 对图片工具来说，大家更想先看到生成表单，还是先看到效果案例？ 3. Prompt Library 这种页面有没有用，还是大家更习惯直接自己写？ 4. 如果你平时会用 AI 生成图，最常用的场景是产品图、头像、封面、广告图，还是别的？ 欢迎拍砖，尤其是 UI 、文案、信息结构这块。 链接再放一次： https://nanobanana2lite.me/