Skip to main content
Add as a preferred source on Google


Stability AI Releases 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 released 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

  • Campus Technology Announces 2025 Product of the Year Winners

    Sixteen companies were selected as winners for their product achievements.

  • AI word on microchip and colorful light spread

    Microsoft Unveils Maia 200 Inference Chip to Cut AI Serving Costs

    Microsoft recently introduced Maia 200, a custom-built accelerator aimed at lowering the cost of running artificial intelligence workloads at cloud scale, as major providers look to curb soaring inference expenses and lessen dependence on Nvidia graphics processors.

  • large group of college students sitting on an academic quad

    Student Readiness: Learning to Learn

    Melissa Loble, Instructure's chief academic officer, recommends a focus on 'readiness' as a broader concept as we try to understand how to build meaningful education experiences that can form a bridge from the university to the workplace. Here, we ask Loble what readiness is and how to offer students the ability to 'learn to learn'.

  • row of digital padlocks

    2026 Cybersecurity Trends to Watch in Higher Education

    In an open call last month, we asked education and industry leaders for their predictions on the cybersecurity landscape for schools, districts, colleges, and universities in 2026. Here's what they told us.