Stability AI

Stable Diffusion 3.5 Medium is here! Whether a startup or creator, access to this technology shouldn’t be restricted by hardware limitations. With 2.5 billion parameters, this model is designed to run “out of the box” on consumer hardware. This model delivers best-in-class image generation for its size, with advanced multi-resolution capabilities. It surpasses other medium-sized models with its prompt adherence and image quality, making it a top choice for efficient, high-quality performance. This model is available for both commercial and non-commercial use under the Stability AI Community License. For Enterprise use, please contact us at: https://lnkd.in/gyfttPQk. 🔗 Learn more about Stable Diffusion 3.5 Medium on our blog: https://lnkd.in/gd2yY-nY

It was a pleasure to sit down with Joseph Gordon-Levitt and Joanna Stern at WSJ Tech Live this week. We had a spirited and important conversation about AI and visual media. I was proud to share the stage with Joseph, an incredible artist and advocate for creators’ rights, to talk about Stability AI’s creator-centric approach to developing AI tools that level the playing field, enabling more artists and storytellers in the world.

Introducing Stable Diffusion 3.5, our most powerful models yet. This open release includes multiple variants that are highly customizable for their size and run on consumer hardware. You can download Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo models from Hugging Face and the inference code on GitHub now. Stable Diffusion 3.5 Medium will be released on October 29th. The Stable Diffusion 3.5 version excels in the following areas while maintaining top-tier performance in prompt adherence and image quality: Customizability: Easily fine-tune the model to meet your specific creative needs, or build applications based on customized workflows. Efficient Performance: Optimized to run on standard consumer hardware without heavy demands, especially the Stable Diffusion 3.5 Medium and Stable Diffusion 3.5 Large Turbo models. Diverse Outputs: Creates images representative of the world, not just one type of person, with different skin tones and features, without the need for extensive prompting. Versatile Styles: Capable of generating a wide range of styles and aesthetics like 3D, photography, painting, line art, and virtually any visual style imaginable. Creator Brad T., put the model to work, exploring its capabilities and shared some of his favorite outputs. Stable Diffusion 3.5 reflects our commitment to empowering builders and creators just like Brad, with cutting-edge and widely accessible tools. These models are freely available for both commercial and non-commercial use in most cases, under the Stability AI Community License. For Enterprise use, please contact us at: https://lnkd.in/gyfttPQk. You can learn more here: https://lnkd.in/gd2yY-nY

Incredible to see how Stride Learning Solutions is using Stable Diffusion on Amazon Web Services (AWS) to enable their students to create images for their story books!

Today, we announced that legendary filmmaker James Cameron has joined the Stability AI Board of Directors. Following this exciting news, Cameron and our CEO, Prem Akkaraju, sat down with Julia Boorstin on CNBC. You can watch a highlight from their conversation here: https://lnkd.in/ge6G_6x6

Today, our CEO, Prem Akkaraju, announced that legendary filmmaker, technology innovator, and visual effects pioneer, James Cameron, has joined the Stability AI Board of Directors. James has been a driving force in merging cutting-edge technology with visionary storytelling. As a director, writer, and producer, he has pushed cinematic boundaries and brought to life some of the most iconic and technologically advanced films of all time, including The Terminator, Aliens, The Abyss, Titanic, and Avatar movies. Cameron’s addition represents a significant step forward in our mission to transform visual media. His artist-centric perspective, paired with his business and technical acumen, will be invaluable as we continue to build a full stack AI pipeline that unlocks new opportunities for creators to tell stories in ways once unimaginable. You can read the full announcement here: https://lnkd.in/gz93cPyM

Interested in fine-tuning your own image models with Stable Diffusion 3 Medium? We've created a tutorial to guide you through fine-tuning Stable Diffusion 3 Medium for high-quality, customized images. If you're familiar with SD1.5 or SDXL, this guide highlights key differences in fine-tuning with SD3M and offers insights to help you get started. You can view the full tutorial here: https://lnkd.in/gkiH3fpv

We’re thrilled to announce that three of our best text-to-image models – Stable Image Ultra, Stable Diffusion 3 Large and Stable Image Core – are now available in Amazon Bedrock. This collaboration delivers our advanced text-to-image models in Amazon Web Services (AWS)’s powerful cloud infrastructure, enabling businesses across industries like media, marketing, retail, and game development to supercharge their visual content creation. 🚀 You can read more about our collaboration here: https://lnkd.in/gaZ3RnWP

Want to bring your creative projects to life? Stable Assistant has all the tools you need! Powered by our latest technology, it has the ability to: 📸 Generate and edit images. 🎥 Create videos. 🧩 Design 3D assets. 🎙️ Craft high-quality audio. And so much more. 📎 If you’re a newcomer on our platform, get started with our comprehensive guide on how to use Stable Assistant: https://lnkd.in/gxAt9FXu

Stuck integrating creative ideas to accelerate content generation? #AWS & Stability AI can walk you through how to build Proof-of-Concepts (PoCs) for #generativeAI using AWS services. 👉 https://go.aws/3SUpsZ4 💡 Explore real-world use cases, best practices, & learn how to leverage the latest #AI advancements to drive innovation in your organization.