Stability AI

We’re pleased to announce that Robert Legato is joining Stability AI as Chief Pipeline Architect! Robert joins with an extensive background in the visual effects and entertainment industry. He is the visual effects pioneer behind such legendary films as Avatar, Titanic, The Lion King (2019), Jungle Book, Apollo 13, Aviator, and Hugo. His work in Hollywood has earned him several accolades, including three Academy Awards and a BAFTA. He has also held roles at Paramount Pictures, Digital Domain, and Sony Pictures Imageworks over his 30-plus year career. As Chief Pipeline Architect, Robert will leverage his deep domain expertise to align our applied research with real VFX industry needs. He will also strengthen collaboration between Stability AI and the VFX industry, translating our cutting-edge visual media models and workflows into practical solutions for production pipelines. You can read our full announcement here: https://bit.ly/3DPzHJQ

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization. A virtual camera is a digital tool used in filmmaking and 3D animation to capture and navigate digital scenes in real-time. Stable Virtual Camera builds upon this concept, combining the familiar control of traditional virtual cameras with the power of generative AI to offer precise, intuitive control over 3D video outputs. Stable Virtual Camera offers advanced capabilities for generating 3D videos, including: ✅ Dynamic Camera Control: Supports custom & preset paths (360°, Lemniscate, Dolly Zoom, Spiral, Pan, Move & more). ✅ Flexible Inputs: Generates 3D videos from just one input image or up to 32. ✅ Multiple Aspect Ratios: Produces square, portrait, landscape & custom aspect ratios, with no additional training required. ✅ Long Video Generation: Maintains 3D consistency for up to 1,000 frames. Currently in research preview, the model is available for use under a Non-Commercial License. You can read the paper, download the weights on Hugging Face, and access the code on GitHub now. Learn more here: https://bit.ly/4ks2xRb

We are excited to announce that Ryan Ellis is joining Stability AI as SVP, Head of Product! Ryan joins from Unity, where he led product development for the world’s most widely used real-time 3D engine, serving 1.5 million developers across gaming, automotive, manufacturing, and retail. At Unity, he focused on how AI is transforming content creation, expanding Unity’s reach beyond gaming, and developing strategic partnerships and alliances with consulting and technology partners. With extensive experience designing tools for professional creators and developer ecosystems, Ryan will focus on building products that enable more people to leverage Stability AI’s cutting-edge models and workflows to create, build, and innovate. You can read the full announcement from our CEO, Prem Akkaraju, here: https://bit.ly/41QMd4U

How are creative professionals integrating generative tools into their media production workflows today? 🤔 There are countless ways—here’s one: A new case study by Amazon Web Services (AWS) highlights how Mercado Libre leveraged Stable Diffusion to generate high-quality product images at scale, achieving a 45% increase in display impressions. To learn more, read the full case study here: https://bit.ly/3XtHIe9

We are excited to announce a strategic partnership and investment by WPP in Stability AI. WPP is a world leader in marketing services and home to industry-leading agency brands. Through this partnership, WPP will leverage Stability AI’s best-in-class open visual media models across image, video, 3D, and audio to craft compelling brand narratives. In turn, WPP’s real-world applications and market insights will help drive the continued development of Stability AI’s transformative technology and creator-centric approach. By establishing a joint R&D pipeline, WPP will gain access to Stability AI’s cutting-edge models and workflows, integrated directly within WPP’s AI-driven operating system, WPP Open, to explore new ways to ideate, perform concept testing, and develop new solutions, further shaping the future of visual media and entertainment. Together, we aim to usher in a new era of innovation at the convergence of creativity and technology. You can learn more here: https://lnkd.in/dJGG7KHz

📲 Audio generation, on-device, off-line, for the first time! We’ve partnered with Arm to bring generative audio to mobile devices, enabling high-quality sound effects and audio sample generation directly on-device with no internet connection required for the first time! By leveraging Arm KleidiAI libraries and our cutting-edge technology, Stable Audio Open, now runs 30x faster on smartphones on Arm CPUs, reducing generation time from minutes to seconds. This breakthrough will be showcased at MWC Barcelona today, demonstrating unprecedented AI-powered content creation at the edge. You can view the full Built on Arm video and learn more here: https://bit.ly/3Xq34ZJ

We’re excited to announce that Stable Diffusion 3.5 Large, Stable Image Ultra and Stable Image Core are now available on Microsoft Azure AI Foundry – providing businesses of all sizes access to professional-grade image generation within their trusted Microsoft ecosystem. By bringing our latest technology to Microsoft Azure AI Foundry, we’re enabling businesses to seamlessly integrate these models into their existing workflows and applications. You can read the full blogpost here: https://bit.ly/4gF4yX0

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. SPAR3D transforms 3D prototyping for game developers, product designers, and environment builders with the following advanced capabilities: ▶️ Unprecedented Control: Allows users to directly edit the point cloud by deleting, duplicating, stretching, adding features, or recoloring points. ▶️ Complete Structure Prediction: Enhances 3D construction by providing accurate geometry and detailed predictions for full 360-degree views, including areas typically hidden, such as the back of an object. ▶️ Lightning-Fast Generation: Converts edited point clouds into final meshes in just 0.3 seconds, enabling seamless real-time editing. From a single input image, it generates highly detailed 3D meshes in only 0.7 seconds per object. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. To learn more about the underlying technology, you can read the full research paper on our blog. Learn more here: https://bit.ly/4a6LNKe  

Now generally available! ✅ By bringing Stable Diffusion 3.5 Large to Amazon Bedrock, we’re meeting builders where they already work – within trusted Amazon Web Services (AWS) environments. This enables startups and enterprises to seamlessly and securely deploy SD3.5 Large without requiring additional infrastructure. We’ve also upgraded our image services on Bedrock, Stable Image Ultra and Stable Image Core, to leverage our most advanced technology and deliver tailored generative AI solutions. To learn more and get started, visit our blog here: https://bit.ly/3VNELEx

This just in from AWS re:Invent... Amazon Web Services (AWS) Swami Sivasubramanian #AWSreInvent