News

Introducing Stable Diffusion 3.5
Product IT Admin Product IT Admin

Introducing Stable Diffusion 3.5

Today we are introducing Stable Diffusion 3.5. This open release includes multiple model variants, including Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo, and as of October 29th, Stable Diffusion 3.5 Medium.

Read More
Stable Audio Open: Research Paper
Research Joshua Lopez Research Joshua Lopez

Stable Audio Open: Research Paper

Following the open source release of Stable Audio Open, we are excited to share the research paper outlining the technical details behind the model. The paper is accessible on arXiv and the model weights are available on Hugging Face.

Read More
License Update
Company, Community Kesh Bhamidipaty Company, Community Kesh Bhamidipaty

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.

Read More
Reflecting on Computex Taipei and the Exciting Journey Ahead 
Company Joshua Lopez Company Joshua Lopez

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.

Read More
Stable Artisan: Media Generation and Editing on Discord
Joshua Lopez Joshua Lopez

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.

Read More
Introducing Stable LM 2 12B
Product Joshua Lopez Product Joshua Lopez

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.

Read More