• Bot Eat Brain
  • Posts
  • Meta launch 3D Gen, a text-to-3D model generator

Meta launch 3D Gen, a text-to-3D model generator

PLUS: Design your dream home with AI

In partnership with

Happy 4th of July, folks. 🇺🇸

Good morning, human brains, and welcome back to your daily munch of AI news.

Here’s what’s on the menu today:

  • Create high-quality 3D models in 60 seconds 🧊 🪩

    Meta launched 3D Gen, a text-to-3D model generator.

  • Design your dream home with AI 🏠 🔥

    Dune dream house, rainforest retreat, and more.

Sponsor Bot Eat Brain and reach over 20,000 readers.

(Now 50% off) 🤯

Peep today's ‘What Would You Do?’ at the bottom. 👇


High-quality 3D models in 60 secs 🧊 🪩

On Tuesday, Meta launched 3D Gen. It’s a text-to-3D asset generation model.

Girl, are you a 3D movie? You're expensive and give me a headache. 🤕

How does it work?

It generates a 3D mesh with physically-based rendering (PBR) from text. Then it creates high-quality, detailed textures that combine into a complete 3D model.

Is it any good?

It outperforms top models in speed, quality, versatility, and more. It creates complex characters and entire scenes that closely follow your instructions.

So, what?

You can use this tool to develop games, product prototypes, architectural visualizations, VR and AR assets, and more.

They have VR for cows now. It’s a moooood enhancer. 🐄 ❤️

An entirely new way to present ideas

Gamma’s AI creates beautiful presentations, websites, and more. No design or coding skills required. Try it free today.


Think Pieces 🧠

How climate-conscious is Google’s environmental report? It contains more than 80 pages detailing its efforts, but doesn’t say how much energy it uses.

Startup News 💰

Meta is changing its AI labels from Made with AI to AI Info. It was incorrectly labeling real photos as AI-generated content.

Amazon proposes new benchmarks to evaluate RAG systems. It uses multiple-choice exams to assess how well RAG implementations handle tasks.

Research 👨‍🔬

MMEvalPro — a benchmark designed to provide trustworthy evaluations of multimodal models by eliminating systematic biases and Type-I errors.

We-Math — a benchmark that evaluates large multimodal models (LMMs) on their visual mathematical reasoning skills.


Here’s Dashi. 🐶

“She’s so worried about not being able to keep up with AI that she’s afraid to look at the news 😆”

Respond to this email with your pet’s name and pic for a chance to be featured here tomorrow!

Get an original business idea delivered straight to your inbox daily.

Join +10,000 others with hundreds of ★★★★★ star reviews.




Free mansion, anyone? 🏠

Choose your home.👇

Home Sweet Home

Choose your house

Login or Subscribe to participate in polls.

Ideas? Comments? Complaints?

Respond to this email or hit me up on 𝕏.

Until next time 🤖😋🧠 

What'd you think of today's newsletter?

Login or Subscribe to participate in polls.