Creative Tools2 weeks ago
Veo 3 AI - Free Veo 3 AI Video Generator With Audio | veo3ai.org
Generate 4K videos from text prompts with AI-rendered visuals, sound effects, and lip-syncing.
Veo 3 AI — Veo 3 AI 视频生成
The full gallery
Tech stack
60 projects
Generate 4K videos from text prompts with AI-rendered visuals, sound effects, and lip-syncing.
Veo 3 AI — Veo 3 AI 视频生成
Generate interactive 3D worlds in seconds with text and photos using AI for games, research, and robotics.
ai world generator — 用文本和照片生成自然风光视频的 AI 工具网站
Generate collectible AI miniature figures from your photos with customization options.
AI miniatur — 将照片转换为 AI 手办模型
Turn story ideas into 3D-printable tactile Braille pages for blind and low-vision children.
@fgiuliani87 · X
What if every blind or visually impaired child could create—and touch—their own story? ✨ Type an idea. We turn it into real Braille and raised illustrations, ready to 3D-print at home. Built with @lovable to make imagination accessible to everyone. 💜
Race through 3D cube environments in this arcade game.
@dominguezdaniel · X
Play here! 🏎️ Built with Codex. Powered by Three.js. Deployed on Vercel.
Create beautiful crystal visualizations and patterns.
@songfeitong · X
Introducing Pretty Lattice, a modern-looking crystal visualization tool for creating beautiful figures. Built with Codex since 5.5, and now with 5.6 sol. A huge leap from 5.5, much better at frond end. Github: Demo:
Turn text and images into cinematic 4K+ videos with native audio, multi-shot sequencing, and persistent character identity.
kling — AI 生成视频，支持多种 kling 模型
Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
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.
Enter your story to create manga panels and videos with AI scenes.
MakeManga — AI 生成漫画，支持 Nano Banana 和 Seedream 4.0 模型，只需提供故事，剩下的分镜和角色生成等都交给 AI
Convert PNG/JPG photos to 3D-printable STL files instantly and free.
Generate framed wall art from your bookshelf.
@Sathibuilds · X
I am building and
Throw virtual jiao cups in 3D to get your divination result.
Demo1024 · V2EX
重看《周处除三害》后，我做了个 3D 掷筊小网站 大家好，我最近重看了一遍《周处除三害》。 然后看到电影里陈桂林在关圣帝君面前连续掷出九次圣杯，随后决定自首。筊杯一次次被抛起，他也在一次次落定的结果面前挣扎，直到不得不作出选择的时候，我突然也想试试掷筊，就是去掷几下玩一下。 结果我搜了半天，发现基本上类似的在线掷筊工具都做的挺拉胯的。基本都是点一下，然后给你个随机的结果，没有过程，没有仪式感。然后我就觉得不如我自己做一个。 所以就和 Codex 协作做出了当前这个版本的 3D 掷筊小网站： https://asklaoye.com/zh-Hans 名字叫「问老爷·掷筊问事」，取名源于潮汕地区，一般把这种请示神明的过程称之为问老爷。 和现在能搜到的那些在线掷筊工具相比，问老爷里的两枚筊杯会经过实际的 3D 物理运动：向上抛起、碰撞、落地，最后根据两枚筊杯停稳后的朝向，判断是圣杯、笑杯还是阴杯。由于我限制了投掷范围为网页全局视口，所以也会出现卡边之类的特殊情况，这个时候就会显示未定结果。 然后网站里面的筊杯的 3D 模型，还是我专门充值了 70