@hannah24_app · X

fran-mora · HN

I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

Canvave — 简单图形设计和动画制作平台。无须专业技能也能做出任意尺寸的精美设计；最高支持图片 3x 或动画 240 FPS 导出；内置基于 Flux 的 AI 文生图、图生图；适合电商卖家、广告设计、社媒运营、独立开发等有设计需求的群体

@VanillaSkyAI · X

is like Lovable for video. Paste a URL, get a launch video, chat to edit, post 🎬 Here's one I made in minutes 👇

@KolhyP92244 · X

@pixelcave_john · X

Hey Germán! I recently launched and a major update to Tailkit!

hjessmith · HN

I like doodling, and I like character animation. I made a little tool that can animate your hand drawn characters and put them into an animated meme. It's free, there's no login needed, and it uses an animation pipeline (not generative AI) to create the outputs. Works on desktop and mobile. If you give it a try, I'd love to hear your feedback. Thanks!

zxhywork · V2EX

Muse Image AI Meta Superintelligence Labs 7 月 7 号发布了他们第一个图像模型 Muse Image ，内部代号 Mango 。玩了两天，这个模型有几个点确实有意思： - **Agentic 生成**：出图前先规划布局，需要事实的场景会联网搜，画完自查一轮再交稿，长 prompt 一次过的概率明显高 - **图内文字能看了**：海报标题、图表、甚至可扫的二维码都能直接画进图里，这是大部分生图模型至今糊掉的地方 - **多参考图合成**：从几张照片里分别取人脸、服装、产品、背景，融成一张不违和的图 官方入口在 Meta AI App / meta.ai / Instagram Stories ，国内用着别扭，还得装 App 。我就照着上一个站的路子做了个纯网页版：[museimages.io]( https://museimages.io/)。 产品上砍得很狠，只做图像，三个入口： - [Meta Muse Image 在线生成器]( https://museimages.io/ai-image-generator)