Skip to main content
Mythos

Stable Diffusion is a family of 🏷️#generative-ai text-to-image models from 📝Stability AI that generate images from text prompts. Stability AI announced its public release in August 2022 under a Creative ML OpenRAIL-M license, which the company described as a permissive license that allows for commercial and non-commercial usage. The current generation, Stable Diffusion 3.5, is released under the Stability AI Community License, which Stability AI offers free to researchers, developers, small businesses, and creators with less than $1M in annual revenue, with an Enterprise license for businesses whose annual revenue exceeds $1M.

In July 2023, Stability AI released SDXL 1.0 as an open model, with a 3.5B parameter base model and a 6.6B parameter model ensemble pipeline. In February 2024 it announced Stable Diffusion 3 in early preview, a suite then ranging from 800M to 8B parameters that combines a diffusion transformer architecture and flow matching. Its October 2024 announcement of Stable Diffusion 3.5 says the earlier Stable Diffusion 3 Medium release "didn't fully meet our standards or our communities’ expectations." The Stable Diffusion 3.5 open release includes Large, Large Turbo, and Medium variants that the company says run on consumer hardware, with the models available on 📝Hugging Face and the inference code on GitHub.

Key Features

  • Stable Diffusion 3.5 Large — An 8.1 billion parameter base model that Stability AI calls the most powerful in the Stable Diffusion family, for professional use at 1 megapixel resolution.
  • Stable Diffusion 3.5 Large Turbo — A distilled version of Stable Diffusion 3.5 Large that generates images in just four steps.
  • Stable Diffusion 3.5 Medium — A 2.5 billion parameter model with the MMDiT-X architecture, designed to run on consumer hardware and to generate images between 0.25 and 2 megapixels.
  • Customizability — Query-Key Normalization in the transformer blocks is meant to simplify fine-tuning and further development of the models.
  • Versatile styles — Generates a wide range of image styles, including 3D, photography, painting, and line art.

Contexts

MythOS is a product of Cooperating Citizens of One, Inc.

TermsPrivacyRefundsContact

© 2026 Cooperating Citizens of One, Inc. · MythOS since 2017 · Not affiliated with Anthropic.