Stable Diffusion XL
Create and inspire using the worlds fastest growing open source AI platform.
With Stable Diffusion XL, you can create descriptive images with shorter prompts and generate words within images. The model is a significant advancement in image generation capabilities, offering enhanced image composition and face generation that results in stunning visuals and realistic aesthetics.
Stable Diffusion XL is currently in beta on DreamStudio and other leading imaging applications. Like all of Stability AI’s foundation models, Stable Diffusion XL will be released as open source for optimal accessibility in the near future.
Highlights of Stable Diffusion XL capabilities
Next-level photorealism capabilities
Image composition and face generation
Use of shorter prompts to create descriptive imagery
Greater capability to produce legible text
Rich visuals and jaw-dropping aesthetics
Discover unlimited imagination in seconds
Glimpses of a herd of wild elephants crossing a savanna
Vintage hot rod with custom flame paint job
Ancient, mysterious temple in a mountain range, surrounded by misty clouds and tall peaks
Beautiful waterfall in a lush jungle, with sunlight shining through the trees
Extend beyond just text-to-image prompting
Stable Diffusion XL offers several ways to modify the images
Inpainting - Edit inside the image
Outpainting - Extend the image outside of the original image
Image-to-image - Prompt a new image using a sourced image
Experience the power of Stable Diffusion XL
A sadhu man in Rishikesh, India meditating near the Ganges river
We provide customized solutions for enterprise API customers wishing to integrate into our scalable platform.
Terms and Conditions*
The license focuses on ethical and legal uses and must accompany any model distribution. The license must also be available to the model's end users in any service built on it.