Stability AI - Maginative

Stability AI Appoints New CEO Amid Financial Struggles

Richard Banfield• June 21, 2024 • 2 min read

This leadership transition is accompanied by a crucial lifeline: a new round of funding led by a group of investors including Sean Parker, the tech entrepreneur famous for co-founding Napster and serving as Facebook's first president.

Stability AI

Stability AI Releases Text-to-Audio Open Weights Model

Richard Banfield• June 5, 2024 • 2 min read

It is an open source text-to-audio model for generating up to 47 seconds of samples and sound effects.

Stability AI

Stability AI Cuts 10% of Staff Following CEO's Exit

Chris McKay• April 18, 2024 • 2 min read

The company cites the need to "right-size" the business after a period of unsustainable growth.

Stability AI

Stability AI Unveils Stable Audio 2.0

Chris McKay• April 3, 2024 • 2 min read

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

Stability AI's CEO Emad Mostaque Resigns

Chris McKay• March 22, 2024 • 2 min read

Mostaque says that he decided to step down to pursue decentralized AI.

Stability AI

Stability AI Unveils Stable Video 3D

Chris McKay• March 19, 2024 • 2 min read

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.

Stability AI

A First Look at Stable Diffusion 3 and What's Coming Next

Chris McKay• February 22, 2024 • 2 min read

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

Stability AI Announces Stable Cascade

Chris McKay• February 13, 2024 • 2 min read

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

Stability AI Releases AudioSparx for Variable-Length Music

Chris McKay• February 9, 2024 • 2 min read

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 Open Source

Stability AI Unveils 1.6B Parameter Stable LM 2 Model

Chris McKay• January 19, 2024 • 2 min read

Benchmark results show Stable LM 2 1.6B achieving state-of-the-art results for a model under 2 billion parameters.

Stability AI

Stablity Releases an AI Coding Assistant that Can Run Offline on Laptops Without a GPU

Richard Banfield• January 16, 2024 • 2 min read

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

Stability AI Introduces Paid Membership Plans

Chris McKay• December 14, 2023 • 1 min read

The new membership structure includes three distinct tiers, catering to a wide range of users, from individual AI enthusiasts to large enterprises.

Stability AI

Stability AI Unveils StableLM Zephyr 3B, To Bring Tiny Yet Powerful LLMs to Edge Devices

Chris McKay• December 7, 2023 • 1 min read

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.

Stability AI AI Ethics

UK Court Advances Getty's Copyright Suit Against Stability AI: A Deep Dive into the Legal Battle

Chris McKay• December 5, 2023 • 2 min read

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 Research

Stability AI Unveils SDXL Turbo for Real-Time Text-to-Image Generation

Chris McKay• November 28, 2023 • 2 min read

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 Research

Stability AI Releases Stable Video Diffusion

Chris McKay• November 21, 2023 • 2 min read

Stability is open-sourcing Stable Video Diffusion and an image-to-video model, for research purposes.

Stability AI

An Early Look at Stability AI's New Text to 3D Model

Chris McKay• November 1, 2023 • 2 min read

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

Stability AI Launches AI-Powered Music and Sound Generation with Stable Audio

Chris McKay• September 13, 2023 • 3 min read

Early audio samples demonstrate Stable Audio's potential for creating diverse musical compositions tailored to user prompts.

Stability AI

Stability AI Unveils First Japanese Vision-Language Model

Chris McKay• September 1, 2023 • 2 min read

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 Open Source

Stability AI Launches Stable Chat Website Research Preview

Chris McKay• August 11, 2023 • 1 min read

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 Open Source

Stability AI Releases Japanese StableLM, The Most Capable Japanese LLM

Chris McKay• August 9, 2023 • 2 min read

The new 7 billion parameter general-purpose language model aims to provide Japanese users with enhanced AI capabilities for text generation.

Research Stability AI

Humans in 4D: Tracking People in 3D Over Time Using Transformers

Chris McKay• August 9, 2023 • 2 min read

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

Stability AI Announces StableCode, An AI Coding Assistant for Developers

Chris McKay• August 8, 2023 • 2 min read

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

Stability AI Releases Stable Diffusion XL 1.0

Chris McKay• July 26, 2023 • 4 min read

Compared to other image generation models, SDXL achieves superior photorealism, artistic style replication across genres, and handling of difficult concepts like hands and text.