Stability AI Cuts 10% of Staff Following CEO's Exit
The company cites the need to "right-size" the business after a period of unsustainable growth.
Stability AI
A collection of 29 posts
Stability AI Unveils Stable Audio 2.0
One of the most remarkable advancements in Stable Audio 2.0 is its ability to generate songs up to three minutes in length, complete with structured compositions that include an intro, development, and outro, as well as stereo sound effects.
Stability AI's CEO Emad Mostaque Resigns
Mostaque says that he decided to step down to pursue decentralized AI.
Stability AI Unveils Stable Video 3D
Unlike previous approaches, Stable Video 3D delivers coherent views from any given angle with proficient generalization, enhancing pose-controllability and ensuring consistent object appearance across multiple views.
A First Look at Stable Diffusion 3 and What's Coming Next
Stable Diffusion 3.0 represents a major upgrade, incorporating a new diffusion transformer architecture and flow matching that promise to accelerate diffusion model performance.
Stability AI Announces Stable Cascade
Stable Cascade represents a significant stride forward in the field of AI-driven image creation, offering unprecedented levels of quality, efficiency, and accessibility.
Stability AI Releases AudioSparx for Variable-Length Music
With its simultaneous prowess at variable-length music and sound generation, AudioSparx 1.0 represents a remarkable consolidation of multiple audio synthesis capabilities into a single model.
Stability AI Unveils 1.6B Parameter Stable LM 2 Model
Benchmark results show Stable LM 2 1.6B achieving state-of-the-art results for a model under 2 billion parameters.
Stablity Releases an AI Coding Assistant that Can Run Offline on Laptops Without a GPU
Stable Code 3b is a 2.7 billion parameter decoder-only language model pre-trained on 1.3 trillion tokens of diverse textual and code datasets.
Stability AI Introduces Paid Membership Plans
The new membership structure includes three distinct tiers, catering to a wide range of users, from individual AI enthusiasts to large enterprises.
Stability AI Unveils StableLM Zephyr 3B, To Bring Tiny Yet Powerful LLMs to Edge Devices
Despite its relatively smaller size - 60% smaller than the 7B models - it competes favorably with larger models like Falcon-4b-Instruct and Llama-2-70b-chat.
UK Court Advances Getty's Copyright Suit Against Stability AI: A Deep Dive into the Legal Battle
The court found that there were unanswered questions and inconsistencies relevant to the determination of the location of the training and development of Stable Diffusion.
Stability AI Unveils SDXL Turbo for Real-Time Text-to-Image Generation
The model uses a new technique called Adversarial Diffusion Distillation which allows it to have many advantages shared with Generative Adversarial Networks such as single-step image outputs, while avoiding artifacts or blurriness often observed in other distillation methods.
Stability AI Releases Stable Video Diffusion
Stability is open-sourcing Stable Video Diffusion and an image-to-video model, for research purposes.
An Early Look at Stability AI's New Text to 3D Model
The 3D files that are generated can be exported in standard .obj format and refined in 3D software like Blender and Maya, or imported in a game engine, such as Unreal Engine 5 or Unity.
Stability AI Launches AI-Powered Music and Sound Generation with Stable Audio
Early audio samples demonstrate Stable Audio's potential for creating diverse musical compositions tailored to user prompts.
Stability AI Unveils First Japanese Vision-Language Model
During testing, the model successfully provided detailed Japanese descriptions of various input images. It also answered basic questions about the content of images, like identifying the number of people or objects.
Stability AI Launches Stable Chat Website Research Preview
The new website provides an opportunity for the open source AI community to directly evaluate and assist in strengthening these state-of-the-art models.
Stability AI Releases Japanese StableLM, The Most Capable Japanese LLM
The new 7 billion parameter general-purpose language model aims to provide Japanese users with enhanced AI capabilities for text generation.
Humans in 4D: Tracking People in 3D Over Time Using Transformers
New research from Berkely present an approach that, given any video in the wild, can jointly reconstruct the underlying humans in 3D, and track them over time.
Stability AI Announces StableCode, An AI Coding Assistant for Developers
Stability AI has announced StableCode, it’s very first LLM generative AI product for coding. StableCode provides AI-assisted coding capabilities that aim to boost programmer productivity and lower barriers to entry for aspiring developers.
While conversational AI assistants like Llama, ChatGPT, and Bard are already capable of writing code, they
Stability AI Releases Stable Diffusion XL 1.0
Compared to other image generation models, SDXL achieves superior photorealism, artistic style replication across genres, and handling of difficult concepts like hands and text.
Stability AI's New FreeWilly Models are The Best Open Access LLMs Available Today
Using innovative synthetic data generation techniques, Stability AI researchers trained both models to reach state-of-the-art performance on reasoning and language tasks.