News
Behind the Compute: Using the New AI Supercomputer
In this installment, we’ll talk about how we plan to utilize this state-of-the-art AI Supercomputer.
This supercomputer ranks among the top 15 globally in terms of sheer power and efficiency.
Stability AI Partners with Jasper in Divestment of Init ML
Today we are pleased to announce the divestment of Init ML, the makers of Clipdrop, to Jasper.
Introducing Stable Cascade
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.
Stability AI Joins U.S. Artificial Intelligence Safety Institute Consortium
Stability AI strengthens its dedication to AI safety and transparency by joining the U.S. Artificial Intelligence Safety Institute Consortium (AISIC) and collaborating with leading organizations across various sectors. This partnership, initiated by the National Institute of Standards and Technology (NIST), aims to foster the safe and responsible development of AI technologies.
Introducing Stable LM 2 1.6B
Today, we are introducing our first language model from the new Stable LM 2 series: the 1.6 billion parameter base model and an instruction-tuned version. The base model is trained on…
Stable Code 3B: Coding on the Edge
Stable Code, an upgrade from Stable Code Alpha 3B, specializes in code completion and outperforms predecessors in efficiency and multi-language support. It is compatible with standard laptops, including non-GPU models, and features capabilities like FIM and expanded context size.
Stable Video Diffusion Now Available on Stability AI Developer Platform API
Stable Diffusion Video API transforms images into 2-second, high-quality videos. Ideal for businesses and researchers, customization, and a competitive edge in various industries like advertising, TV, and gaming.
Introducing the Stability AI Membership
Stability AI Membership provides commercial rights to our core models across multiple modalities. Our three membership tiers - Non-Commercial, Professional, and Enterprise - make AI technology accessible to all.
Introducing Stable Zero123: Quality 3D Object Generation from Single Images
Stable Zero123 is an AI-powered model for generating novel views of 3D objects with improved quality. Released for non-commercial and research purposes, it uses an improved dataset and elevation conditioning for higher-quality predictions.
Behind the Compute: Building the New AI Supercomputer
Stability AI has partnered with Intel to build a new accessible, affordable, and scalable AI supercomputer using Intel's Gaudi 2 AI accelerator.
Introducing Stable LM Zephyr 3B: A New Addition to Stable LM, Bringing Powerful LLM Assistants to Edge Devices
StableLM Zephyr 3B is a new chat model representing the latest iteration in our series of lightweight LLMs, preference tuned for instruction following and Q&A-type tasks.
Introducing Japanese Stable LM Beta
Introducing Stability AI Japan's JSLM Beta series – the latest in Japanese language technology. Tailored for Japan, these models, including the powerful JSLM Beta 70B, redefine language processing with 70 billion parameters.
Statement to the U.S. Senate AI Insight Forum on Transparency, Explainability, and Copyright
It is more important than ever that we can scrutinize these systems before the next wave of digital services and digital ventures are built on “black box” technology operated by a small cluster of Big Tech firms.
Introducing SDXL Turbo: A Real-Time Text-to-Image Generation Model
SDXL Turbo is a new text-to-image mode based on a novel distillation technique called Adversarial Diffusion Distillation (ADD), enabling the model to create image outputs in a single step and generate real-time text-to-image outputs while maintaining high sampling fidelity.
Introducing Stable Video Diffusion
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.
Clipdrop Launches Real Estate Tools
Clipdrop has released a compiled list of Real Estate tools, a suite of tailored AI enhancements specialized for architects and real estate designers.
Stability AI Previews Enhanced Image Offerings: APIs for Business & New Product Features
Stability AI is excited to share updates regarding our next generation text-to-image products, featuring private previews of upcoming business offerings, including enterprise-grade APIs and new image enhancement capabilities.
Stable Audio Named One of TIME’s Best Inventions of 2023
We’re pleased to announce Stable Audio has been named one of TIME’s Best Inventions of 2023!
License Update
Our new Community License is now free for research, non-commercial, and commercial use. You only need a paid Enterprise license if your yearly revenues exceed USD$1M and you use Stability AI models in commercial products or services.
Stability AI Secures Significant New Investment from World-Class Investor Group and Appoints Prem Akkaraju as CEO
Stability AI Secures Significant New Investment from World-Class Investor Group and Appoints Prem Akkaraju as CEO.
Announcing the Open Release of Stable Diffusion 3 Medium, Our Most Sophisticated Image Generation Model to Date
We are excited to announce the launch of Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series.
Reflecting on Computex Taipei and the Exciting Journey Ahead
Computex Taipei, Asia’s largest tech event, saw groundbreaking announcements from AMD, Intel, and Nvidia. Stability AI was proud to share the stage with some of the brightest minds in tech and AI, where our co-CEO Christian Laforte announced the upcoming launch of Stable Diffusion 3 Medium, our most advanced image generation product.
Introducing Stable Audio Open - An Open Source Model for Audio Samples and Sound Design
We’re excited to announce Stable Audio Open, an open source model optimised for generating short audio samples, sound effects and production elements using text prompts.
Stable Artisan: Media Generation and Editing on Discord
One of the most frequent requests from the Stable Diffusion community is the ability to use our models directly on Discord. Today, we are excited to introduce Stable Artisan, a user-friendly bot for media generation on Discord.
Stability AI Joins Thorn and All Tech Is Human to Enact Child Safety Commitments for Generative AI
We have joined Thorn, All Tech is Human, and other leading companies in the effort to prevent the misuse of generative AI technologies to perpetrate, proliferate, and further sexual harms against children.
Stable Diffusion 3 API Now Available
We are pleased to announce the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo on the Stability AI Developer Platform API.
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
Continuing research into neuroscience and machine learning, today MedARC releases a state-of-the-art fMRI-to-image reconstruction model that is shown to work well with just 1 hour of training data.
Introducing Stable LM 2 12B
Introducing the latest additions to our Stable LM 2 language model series: a 12 billion parameter base model and an instruction-tuned variant, trained on 2 trillion tokens in seven languages: English, Spanish, German, Italian, French, Portuguese, and Dutch. This medium-sized model balances strong performance, efficiency, memory requirements, and speed, following our established Stable LM 2 1.6B framework as detailed in our previously released technical report.