AI tools
March 26, 2024

This AI Tool Can Generate 3D Models in 5 Seconds

Fast 3D model generation with AI is now possible with LGM.

Jim Clyde Monge
Jim Clyde Monge

3D content generation with an AI solution has seen some significant progress in recent months. A few weeks ago, I wrote an article about Genie from Luma Labs, an impressive AI solution for creating 3D models from text descriptions.

However, one drawback with Genie is that the generation process can take around 10 minutes to complete.

Now, a new solution named LGM promises to slash that time dramatically, generating 3D models in just 5 seconds.

How true is that? Let’s find out.

What is LGM?

LGM (Large Multi-View Gaussian Model) represents a novel framework that produces high-resolution 3D models from simple text descriptions or even single images.

How LGM (Large Multi-View Gaussian Model) works
How LGM (Large Multi-View Gaussian Model) works

It uses an asymmetric U-Net backbone along with multi-view diffusion models. This tech combo enables near-instant 3D creation, addressing the resolution and fidelity issues found in earlier models.

If you want to know more about how LGM works, check out this white paper.

Free Demo (Try it yourself)

Head over to LGM’s HuggingFace page and start typing the description of the 3D object you want to generate. For instance, I wanted to generate a 3D model of a teddy bear.

Prompt: teddy bear

LGM text to 3D. Prompt: teddy bear
Image by Jim Clyde Monge

Here’s a preview of the generated 3D model:

LGM text to 3D Prompt: teddy bear example
GIF by Jim Clyde Monge

This 3D model looked fantastic! All the angles seem to be correct, and despite being viewed from different angles, the model stays consistent—no weird distortions.

Now let’s try a more complex model and see how well the AI can generate it.

Prompt: Ducati Hypermotard 939

LGM text to 3D. Prompt: Ducati Hypermotard 939
Image by Jim Clyde Monge

Unfortunately, while the separate preview images appeared promising, the complete 3D model wasn’t as successful.

Image to 3D

Aside from the text-to-3D capability, LGM also supports 3D object generation from an input image.

LGM image to 3D example with a frog image
Image by Jim Clyde Monge

The generated 3D model maintained its shape and structure impressively well, another sign of the AI’s understanding of form.

LGM image to 3D example with a frog image
GIF by Jim Clyde Monge

Here are more examples from LGM’s project page:

LGM text to 3D examples
LGM Text to 3D

Why does this matter?

  • Pros: This type of technology is potentially revolutionary for 3D modeling. Artists gain a lightning-fast way to brainstorm and build assets. Game developers could streamline workflows, accelerating prototyping and production.
  • Cons: As with any technological leap, there are downsides. Some 3D artists may resist adopting these tools and fall behind the curve. Marketplaces selling stock 3D assets might see major shake-ups. Even big companies like Adobe and Autodesk, giants in 3D modeling software, could face disruption as AI makes workflows simpler and more accessible.

What’s next?

Imagine how this AI solution could transform several industries.

  • Gaming: More dynamic, detailed game worlds built faster than ever.
  • Animation: Characters and environments brought to life with unprecedented speed and ease.
  • 3D Printing: Physical object design and rapid prototyping could become accessible to far more people.
  • Architecture: More intricate designs, visualized and iterated on in the blink of an eye.

There is an ongoing competition

If you think this is a novel technology, it is not. There have been a few AI-powered 3D model generators out there. A few that I have already covered here on Medium are the following:

This competition is a great thing! It fuels innovation and drives the researchers to make their tools even better, faster, and more accessible.

Final Thoughts

Overall, I am happy to see yet another AI tool that can generate 3D objects with nothing but a text description or an image. This is my first time seeing a solution that can take an image as an input and generate a cohesive and decent-quality 3D model as an output.

While it’s crucial to remain mindful of the potential challenges this technology poses, its sheer creative potential is undeniable. LGM is truly a leap forward, and I’m excited to see how the developers and researchers can improve their solution to actually generate a downloadable 3D model similar to Luma Lab’s solution.