Intel has just launched LDM3D, a new generative artificial intelligence capable of creating 360-degree virtual environments in 3D from a written request. Artificial intelligence is available under a free license.
You will also be interested
[EN VIDÉO] Artificial intelligence adjusts the angle of the photo Point-based interactive manipulation of the generative image collector. © Dragan Project
Intel Labs has just launched a new kind of generative AI. AI systems capable of generating an image from a sentence, like Midjourney or Dall-E, are starting to look pretty good. However, these images are always two-dimensional. In collaboration with Blockade Labs, IntelIntel Labs announced its LDM3D model (potential SpreadSpread 3D model) to generate 360° and 3D images.
LDM3D is based on a specialized version of Stable Diffusion version 1.4. The AI generates a 360-degree image of a 2D environment, along with a depth map (Depth map) which contains information about their relative distance pixelspixels. This model can generate a serene forest, an urban landscape, or even a futuristic sci-fi world in just a few moments.
Some examples of environments created with LDM3D. Drag the photos to explore them in 360 degrees. © Intel Labs, Blockade Labs
Model released under a free license
The two teams then created DepthFusion, a system that uses the TouchDesigner visual programming language to create ” expertise DigitalDigital immersive and interactive In other words, it combines an image and a depth map to create a 3D and 360-degree virtual environment.
The images generated by LDM3D can revolutionize content creation for virtual reality and the metaverse, as well video gamesvideo games And even architecture. The form is available as a free program on the site face hugging.
