Stability AI has launched Stable Diffusion 3 Medium, a text-to-image open-source AI model, in public preview.
The model has 2 billion parameters and utilizes a Diffusion Transformer Architecture. It can be fine-tuned using small datasets. Additionally, the model can generate photorealistic images, adhere to complex text prompts and styles, render text without spelling errors, and is claimed to be resource-efficient.
The model can be accessed via the company’s API and is released under the Stability non-commercial research community license.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.