Emad Mostaque is stepping down as CEO of Stability AI. The company will be led by two interim co-CEOs, COO Shan Shan Wong and CTO Christian Laforte. Mostaque stepped down partly due to the push toward the development of commercialized AI products. He says he is leaving the company to pursue decentralized AI.

Emad Mostaque, a prominent and divisive figure, has resigned as CEO of Stability AI to pursue decentralized AI. Stability AI's COO and CTO are now Co-CEOs as the company searches for a permanent figure.

Stable Diffusion 3, with its novel Multimodal Diffusion Transformer architecture, surpasses leading text-to-image models by enhancing prompt comprehension and typography through separate processing weights for text and images, promising advancements in AI-generated visual content.

Built on top of Stable Video, Stable Video 3D can generate 3D models from a single image. It outperforms Stable Zero 123 and other methods. Weights are available for research purposes and commercial use with a Stability AI membership.

Stability AI's research scientist Robin Rombach, crucial to developing the Stable Diffusion model, is leaving the company, marking a significant departure amidst a year of technical team changes.

Stability AI has announced the next generation of its music generation model. Trained on properly licensed music, the model can generate up to 3 minutes of high-quality music. It also has audio-to-audio generation.

Stability AI has laid off about 20 workers.

Stability AI has released its next-generation Stable Diffusion 3 generative AI model. The model is now available for use via an API on the Stability AI developer platform. Making the model production-ready was a key focus for the company as part of the API release. Stability AI has implemented a number of safeguards to prevent the model's misuse. It is planning to release an open model soon. Stability AI has also just released an early beta preview of Stable Assistant, a chatbot powered by Stability AI's text and image generation technology.

Stability AI has made its latest text-to-image AI model, Stable Diffusion 3, available to some developers via API and its new content creation platform called Stable Assistant Beta. The model is still in preview and not yet available to the general public.

This paper describes Stability AI's diffusion transformer model for audio synthesis.

High-profile AI startups like Inflection AI, Stability AI, and Anthropic are facing financial pressures as they struggle with the high costs of developing generative AI models. While OpenAI, backed by Microsoft, has shown revenue growth, competitors like Anthropic and Stability AI grapple with substantial gaps between revenue and operating expenses. Microsoft's investment in AI hints at the tech industry's belief in AI's long-term profitability, despite the current challenges in monetizing these expensive technologies.

Stability AI has introduced Stable Artisan, a system combining all of its models that can be run from Discord. This is likely a play to compete directly with Midjourney.

Stability AI is in big financial trouble and is in talks to be sold off. The company generated less than $5 million in revenue in the first quarter of this year while losing more than $30 million. It is reportedly sitting on $100 million worth of outstanding bills. The company lost its CEO Emad Mostaque in March and it is currently facing legal troubles over using Getty Images' intellectual property to train AI models.

Stability AI has released SD 3 weights for non-commercial use, with commercial use available on request.

Stable Diffusion 3 Medium is out. A cutting-edge text-to-image model that generates photorealistic images with 2 billion parameters, it overcomes common artifacts in hands and faces, handles complex prompts, and features enhanced typography. Despite recent legal and financial challenges, Stability AI continues to push the boundaries of generative AI, with future upgrades planned across video, audio, and language.

In addition to a new CEO, Stability AI was able to secure a “significant infusion of capital” from existing and new investors.

Stability AI has unveiled Stable Video 4D, a novel generative AI model built on its existing Stable Video Diffusion and Stable Video 3D models. Unlike traditional 3D models, Stable Video 4D produces videos from 8 different perspectives over time using dynamic object datasets. This cutting-edge technology is expected to be influential in sectors like movie production, gaming, and AR/VR.

Stability AI's new tool, Stable Fast 3D, can transform a single image into a 3D model in under a second, reducing the time and cost of creating digital environments. This AI-driven modeler produces high-quality, UV unwrapped 3D assets with realistic textures, making it valuable for architecture, video games, and virtual reality. Its speed and accuracy offer a significant advantage for designers.

Decorated filmmaker James Cameron has joined the board of generative media company Stability AI to guide its transition into visual storytelling.