Intel has just released LDM3D, a new Generative Artificial Intelligence capable of creating 360° 3D virtual environments upon written request. The AI is available under a free license.
You will also be interested
[EN VIDÉO] An artificial intelligence that adjusts the shooting angle of the photo. Interactive manipulation based on generative image collector points. © DragAN project
Intel Labs just launched a new breed of generative artificial intelligence. AIs capable of generating an image from a sentence, like Midjourney or Dall-E, are now quite well known. However, these images are always two-dimensional. In collaboration with Blockade Labs, Intel announced its Latent DiffusionDiffusion Model for 3D (LDM3D) model for generating 360° and three-dimensional images.
LDM3D is based on a special version of Stable Diffusion Version 1.4. The AI creates a two-dimensional image of a 360-degree environment along with a depth map that contains information about the relative distance of each pixel. This model can create a peaceful forest, a cityscape, or even a futuristic sci-fi world in just a few moments.
Some examples of environments generated by LDM3D. Drag the images to explore them in 360 degrees. © Intel Labs, Blockade Labs
A model released under a free license
The two teams then developed DepthFusion, a system that uses the TouchDesigner visual programming language to create “immersive and interactive digital digital experiences.” In other words, it combines the image and the depth map to create a 3D and 360-degree virtual environment.
The images generated by LDM3D could revolutionize the creation of content for virtual reality and the metaverse, as well as video games and even architecture. The pattern is available as free software on the Hugging Face website.