Stability AI Intros Stable Diffusion 3.5 Text-to-Image Generation Model

  • By John K. Waters
  • 11/06/24

Stability AI, developer of open source models focused on text-to-image generation, has introduced Stable Diffusion 3.5, the latest version of its deep learning, text-to-image model.

This release features three enhanced open-source text-to-image models designed for a diverse range of users, including researchers, enterprise clients, and hobbyists, the company said in a statement.

  •  Stable Diffusion 3.5 Large: At 8.1 billion parameters, with superior quality and prompt adherence, this base model is the most powerful in the Stable Diffusion family. This model is ideal for professional use cases at 1 megapixel resolution.
  • Stable Diffusion 3.5 Large Turbo: A distilled version of Stable Diffusion 3.5 Large generates high-quality images with exceptional prompt adherence in just 4 steps, making it considerably faster than Stable Diffusion 3.5 Large.
  •  Stable Diffusion 3.5 Medium: At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run "out of the box" on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25- and 2-megapixel resolution. 

The release follows the earlier debut of Stable Diffusion 3 Medium in June, which the company acknowledged as falling short of both community and internal expectations.

"We chose to build a solution that could truly transform visual media rather than a quick fix," the company said. This latest update is aimed at reclaiming Stability AI's competitive edge amid rising competition from platforms such as OpenAI's DALL-E and Midjourney.

A key technical feature of the new models is Query-Key Normalization within the AI's transformer blocks, which Stability AI said enhances customization and prompt adherence. This modification supports developers and creatives in achieving more consistent results with precise prompts while also allowing broader interpretation with less specific prompts.

"In developing the models, we prioritized customizability to offer a flexible base to build upon," the company explained. "To achieve this, we integrated Query-Key Normalization into the transformer blocks, stabilizing the model training process and simplifying further fine-tuning and development."

The new Stable Diffusion models will be available under Stability AI's Community License, allowing free non-commercial use and free commercial use for entities earning under $1 million annually. Those exceeding this threshold will require an enterprise license. The models, including weights for self-hosting, will be accessible on Hugging Face and via Stability AI's API. ControlNets, offering advanced image customization options, are expected in the coming days.

About the Author

John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS.  He can be reached at [email protected].

Featured

  • digital illustration of Estonia with glowing neural network-like connections spreading across the map

    Estonia to Roll Out ChatGPT Edu for all Secondary Schools

    In a nationwide artificial intelligence program dubbed "AI Leap 2025," the country of Estonia plans to provide free access to leading AI applications for all secondary school students and teachers. The initiative will launch with a rollout of ChatGPT Edu to 20,000 high school students in grades 10-11 and their 3,000 teachers, beginning Sept. 1.

  • pattern of icons for math and reading, including a pi symbol, calculator, and open book

    HMH Launches Personalized Path Solution

    Adaptive learning company HMH has introduced HMH Personalized Path, a K-8 ELA and math product that combines intervention curriculum, adaptive practice, and assessment for students of all achievement levels.

  • laptop screen displaying a typed essay, on a child

    McGraw Hill Acquires Essaypop Digital Learning Tool

    Education company McGraw Hill has announced the acquisition of Essaypop, a cloud-based writing tool that will enhance the former's portfolio of personalized learning capabilities.

  • teacher

    6 Policy Recommendations for Adopting AI in the Classroom

    The Southern Regional Education Board's Commission on AI in Education has published six recommendations on adopting artificial intelligence in schools, colleges, and universities. The guidance marks the commission's first release since it was established last February, with more recommendations planned in the coming year.