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

  • school building protected by a glowing blue shield with circuit patterns, blocking red-orange cyber threat icons

    Establishing a Proactive Defense Against Evolving Cyber Threats

    Here are six good starting points for K-12 districts that want to improve their cybersecurity mitigation strategies and take a more proactive approach to mitigating risk.

  • Stylized illustration showing cybersecurity elements like shields, padlocks, and secure cloud icons on a neutral, minimalist digital background

    Microsoft Announces Host of Security Advancements

    Microsoft has announced major cybersecurity advancements across its product portfolio and practices. The work is part of its Secure Future Initiative (SFI), a multiyear cybersecurity transformation the company calls the largest engineering project in company history.

  • A geometric pattern of open Chromebook computers with bold outlines, subtle shading, and soft gradients, spaced evenly with vibrant green and blue accents on a neutral background.

    Challenges and Opportunities Ahead for the 'Great Chromebook Refresh'

    During the pandemic, the education community scrambled to provide students with laptops to promote online learning equity and mitigate learning loss. Today, those devices are approaching the end of their useful lives — and a "great Chromebook refresh" has been predicted as schools seek to replace them with newer models.  

  • young child sitting at a table, using a tablet with an AI-generated interface

    Research: 1 in 3 Kids Use AI for Learning

    In a survey of parents with children aged 8 or younger, nearly a third of respondents (29%) said their child has used AI for school-related learning, according to a new report from Common Sense Media.