News
Stable Diffusion 3
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.
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.
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!