Today, we’re introducing SceneScript, a novel method for reconstructing environments and representing the layout of physical spaces.

In this paper, we discuss the use of virtual reality as a tool for actors during the rehearsal process and assess methods to implement and continue this research in future works. During the rehearsal process, the scenic design is normally introduced to actors close to the end of rehearsals. In int...

Following our announcement of the early preview of Stable Diffusion 3, today we are publishing the research paper which outlines the technical details of our upcoming model release, and invite you to sign up for the waitlist to participate in the early preview.

TL;DR: We over-parameterize cameras as bundles of rays and propose a diffusion-based framework to predict this representations probabilistically.

Announcing Stable Diffusion 3 in early preview, our most capable text-to-image model with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.

Today marks the launch of Stable Cascade in its research preview. This innovative text to image model introduces an interesting three-stage approach, setting new benchmarks for quality, flexibility, fine-tuning, and efficiency with a focus on further eliminating hardware barriers.

Meet Tong Tong: The revolutionary AI child blending technology and emotion, setting a new standard for artificial intelligence.

Welcome to the Vision Pro, Apple’s most complex piece of hardware yet. So complicated that we’ll need more than one teardown to tackle it. First up: Those creepy eyes.

We offer a highly realistic and top-notch virtual try-on experience based on proprietary AR technology

Freeaim VR are developing a compact and low-cost VR locomotion system that provides a natural and realistic experience, aimed at business and consumer.

Join the discussion on this paper page

I tried these Ray-Ban AI glasses, and they're pretty wild. Here's how the experimental feature works.

Google’s cookie-killing “Privacy Sandbox” project is finally set to begin.

Add eye tracking super powers to your XR systems. Use the XR headsets you already own, and augment it with our drop-in eye tracking add-ons. Get direct access to all raw data with open data formats. Integrate and prototype with us!

Get expert advice from the Apple design team on creating experiences for Apple Vision Pro.

Explore the history of Disney technology, from classic animation innovations to the digital transformation.

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

The comprehensive guide to the state of machine learning in Rust. This site catalogs ML frameworks, data structures, data cleaning and analysis, and other tools and libraries that are essential to machine learning ecosystems.

"I had a full panic attack in the street."

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

DALL·E image → GPT4 Vision → repeat

Stable Video Diffusion is a proud addition to our diverse range of open-source models. Spanning across modalities including image, language, audio, 3D, and code, our portfolio is a testament to Stability AI’s dedication to amplifying human intelligence.

The artists gave me a texture for the moon in III. I placed the moon in the sky, made sure it was visible at night and that it was a reasona...

Site Reliability Engineering, incident management, learning, lessons learned, SRE

For Full Screen, hit F, or View > View in Fullscreen in the notebook menu above. Appendix Image source: https://en.wikipedia.org/wiki/Raptor_Lake Source of Photo: https://en.wikipedia.org/wiki/Raptor_Lake

AI makes it easy to tamper with images online, but an MIT-built system subtly alters them to foil the manipulation.

This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution.

Using magnetoencephalography (MEG), Meta showcases an AI system capable of decoding the unfolding of visual representations in the brain with an unprecedented temporal resolution.