Bet you never saw this coming! Stable Diffusion 3.5 just dropped! We are excited to announce our day 1 support for the Stable Diffusion 3.5 model series! Follow our blog to get started on SD3.5, or use the beta “missing model” feature to download models. No skill is required!

Stable Diffusion 3.5 Large is now available on Replicate. Generate higher-resolution images with finer details and more variety with the new model from Stability AI.

Introducing Stable Diffusion 3.5, Stability AI’s most powerful models yet.  This open release includes multiple variants that are highly customizable for their size, run on consumer hardware, and are free for both commercial and non-commercial use under the permissive Stability

We're so back 🤗

Stable Diffusion 3.5 Medium by Stability AI is live on Replicate: replicate.com/stability-ai/s… It's a 2.5 billion parameter text-to-image model that's built to be able to run on consumer hardware, as well as cloud GPUs.

🎉 Congratulations to Stability AI for securing the win in the AI category, sponsored by AutoGPT at the OpenUK Awards2024! #openukawards #opensource #opensourceai

Introducing Agent TCP/IP: An experimental framework that lets agents trade IP with each other. Agents can now exchange their training data, creative style, investment strategies, and more, ushering in an intelligence economy. 👇

SPAR3D app is now up on Hugging Face Spaces 🔥 > New sota single image-to-3D model from Stability AI > Generates point clouds as intermediate representation before producing the mesh. You can edit the point cloud to adjust the final mesh. > The Gradio app provides a simple point

Dear friends, as RAS and Dataland, we are starting a Web3 Funds for artists affected by devastating fires in Los Angeles. I'll add funds personally, donate Winds of Yawanawa, and more. Our email is [email protected] and if you would like to support it, here is Fund ETH

👏

'I’ve always loved working with visual artists and following on from the competition that we ran with Stability AI around the release of i/o, we are setting up 5050 to encourage the creation of more of these collaborations. So if you have any type of visual work that you would

School just changed forever. ChatGPT is secretly lifting grades and unlocking big-brain thinking according to this research link in comment

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast,

Super excited to launch Stable Audio Open Small today! It was great working with Arm on this model to make sure it runs efficiently on Arm CPUs. I'm also now an Arm Ambassador! I'm looking forward to helping the Arm developer community integrate this new model.

Great to be working with the elite Arm team 💪

AI Media tools coming to Endless 👏

In a world where AI can generate content at scale, Story is building the infrastructure to prove who created what with World . Authorship matters more than ever—and Story is where verified human identity meets programmable IP. Proud to partner with World to bring

Stable Diffusion 3.5 now runs 1.8x faster with the @NVIDIA NIM microservice ⚡ Our collaboration with @NVIDIA delivers faster performance and streamlined enterprise deployment for our most advanced image models. Compared to the base @Pytorch models these performance gains

Drive faster AI innovation with 1.8x quicker image generation and streamlined enterprise deployment — powered by NVIDIA’s NIM microservice for Stable Diffusion 3.5.

Are you curious about running generative AI models right on your Android device? Join Arm and Stability AI in a live code-along and expert Q&A, where you'll convert and run the Stable Audio Open Small model using LiteRT on Arm based Android devices. arm.com/resources/webi…