Builder and Content Creator @DesignCodeio Youtube Tutorials: https://xitter.cf/t.co/OAcQzsCzzP
Joined November 2023
- Tweets322
- Following181
- Followers542
- Likes305
Pinned Tweet
Turn photos into 3d model
Let me know if you want the template for free, I'll send it to you
I made this super detailed OP-XY 3d model with simple prompts and good references. You can use this workflow to create your own 3d models from anything, photos, ai images, pdf, links etc
prompts in the youtube video: youtu.be/j8FPbAsGfxE
Insane sci-fi hangar, red underglow on the ship, cables everywhere on the floor, all of it built by talking to an iPhone
This was done in Houdini, could have been done in Blender too, color grading in Davinci Resolve
Opus 5.5 + Houdini + DaVinci + your phone, crazy
En esta prueba he querido poner Claude al límite con Houdini (modelo Opus 5.5). He montado toda la escena hablándole al iPhone para ver dónde está el límite, y mi conclusión es que no hay límite. Esto que veis es donde he puesto el freno, hay cosas que corregir aún pero quiero seguir experimentando con otros proyectos.
El render ha tardado 50 horas en mi 5090 dado lo compleja que es la escena, volumétricas etc.
El color grading lo he hecho en Davinci trabajando en Aces y también lo hice hablándole al teléfono con el MCP de Davinci.
Me cuesta imaginar un futuro donde no vayamos a trabajar con esto de forma masiva.
2D image to a working 3D carriage
doors, hinges, suspension, flickering lamps, zero modeling, perfect for a website showroom
Gemini 4 Argon + Three.js
兄弟们，看了一圈 Gemini 4 Argon 在2D转3D方面确实遥遥领先。别再以为搞 3D 必须开 Blender 熬夜雕面调骨骼了。
看看原推这玩意儿，直接把我给看清醒了：
给模型一张 2D 维多利亚马车图，零人工参与，纯靠代码直接吐出了一个完整的 WebGL 交互级 3D 资产！扒了一下原推的关键实测数据，极其哈人：
1. 纯代码暴力建构：整整 17.4 万面（Face），没动哪怕一秒 Blender，全是程序化几何直接生成；
2. 带复杂物理装配：不是死模型！车门能开合、车窗带铰链、车轮自带真实的悬挂与回弹物理；
3. 高阶细节与着色：车头的提灯自带动态烛光闪烁，甚至车身上还雕刻了完整的立体骷髅浮雕。大部分人以为大模型只会写两行前端页面或者生成 2D 废话。
真正的技术降维是：大模型正在把图形学渲染管线和几何拓扑当成底层指令直接编译。独立开发者以后做 3D 网页展厅、轻量小游戏，生产力直接被暴力拉平几百倍。
懂 Three.js 和 WebGL 渲染管线的兄弟帮掌掌眼，这种代码生成的拓扑放移动端能扛住几帧？👇
Gemini 4 Argon built this in blender
the loop: reference images, blueprints, specialist agents for joinery, roofing, botany, and an adversarial critic comparing renders against the refs for 30+ passes.
Ok, anyone who wanted to build games in the past but couldn’t because of the technical side can now do it.
games are about creativity and I think all gamers deep inside want to build their own game. Now that AI can take care of the coding, it's going to be crazy fast.
assets, story, music, sfx, visuals can all be created by agents. It gives everyone a chance. Fun times ahead.
I am not joking when I say this.
Traditional game development is over.
I asked Opus-5.5 to make Attack on Titan in Minecraft. Took ~1hr and cost less than $25 start to finish.
The end result is extremely fun. And multiplayer!
Guide + link to play below.
I made this promo video with Opus 5.5 in Blender.
You can use these techniques for way more than just promo videos. It's real 3D work you can use in your actual projects: hero sections, logo animations, icon animations or any component, launch videos.
The music is temporary, and you can absolutely tweak anything you see here with just a bit of Blender knowledge (it's free).
Finally a new Haiku model!
$0.10 in, $0.50 out per million, 1M context
cache hits at $0.01, perfect for agent loops re-reading the same context, which was the expensive part in agentic workflows
it's also the first Claude model priced by prompt length, go over 100K tokens and every rate jumps 5x
Under 100K it's a 10x cut vs Haiku 4.5
This is the most valuable kind of resource right now, not just the outputs, the prompts next to them.
Seeing the instruction beside the result is how you actually learn to direct these tools.
Bookmark to come back for inspirations
prompt-motion.com/
I built a growing gallery of motion graphics made with Claude Opus 5.5, each shown next to the prompt or skill that made it.
226 so far, all pulled from posts here and credited to their creators.
prompt-motion.com
This is big
200+ WebGPU components, open source, export to any framework, free
use them in your next project, amazing
Big news.
Shaders is now open source 🔥
Use any of our 200+ WebGPU components in your work. Ship magic in a client site, a template, a product, a library, anything. Plus, you can export code for any framework, for free.
Give it a star: github.com/shader-effects-in…
Love this one
This is why procedural thinking is the most underrated design skill. You're not sculpting one rock, you're designing the system that makes every rock. Same shift happening in web design right now.
this is so beautiful
the concept is unique and satisfying. animation is stunning
This is historic and will lead to great ai advancements.
The biggest problem is heat, how to cool down TPUs in space. These first tests will give great insights and I have no doubt that we will have brains orbitting our planet in the very near future. If they solve this, there are no reasons to keep ML on earth beside for latency.
We are right now limited by ressources(mostly electricity) and space is big and we can gather way more solar power up there.
It will not only be beneficial for machine learning, but for space exploration in general as well. What a time to be alive
Project Suncatcher has liftoff! ☀️🚀
Announced last year, this moonshot project explores if we can one day host machine learning infrastructure in space. After years of research, we’ve just launched a prototype satellite, built in partnership with @planet, into orbit on @SpaceX's Transporter-18 rideshare mission.
This initial mission will gather data on how @Google TPUs handle the physical stress and extremes of spaceflight. Ultimately, these findings will help us explore how to potentially link multiple satellite constellations for scaled machine learning. By operating in low Earth orbit, these systems can tap into near-constant sunlight to generate up to 8x more solar power than on Earth.
I always said that Google has everything to win the ai race
They have their own chips, infrastructure and the data, the sleeping giant is awakening soon
This quoted post is unavailable.
Just made this component with Sonnet 5.5
open-source library coming soon, make sure to follow
Opus 5.5 was already incredible with usage and now Sonnet 5.5 is even crazier, 50% cheaper, amazing results
prompt below
@claudeai @ClaudeDevs
Prompt: gist.github.com/vannarotroeu…
