SDXL 1.0 foundation model from Stability AI now available in Amazon SageMaker JumpStart
Starting today, the Stable Diffusion XL 1.0 (SDXL 1.0) foundation model from Stability AI is available in Amazon SageMaker JumpStart, a machine learning (ML) hub that offers pretrained models, built-in algorithms, and pre-built solutions to help you quickly get started with ML. You can deploy and use SDXL 1.0 with a few clicks in SageMaker Studio or programmatically through the SageMaker Python SDK.
Starting today, the Stable Diffusion XL 1.0 (SDXL 1.0) foundation model from Stability AI is available in Amazon SageMaker JumpStart, a machine learning (ML) hub that offers pretrained models, built-in algorithms, and pre-built solutions to help you quickly get started with ML. You can deploy and use SDXL 1.0 with a few clicks in SageMaker Studio or programmatically through the SageMaker Python SDK.
SDXL 1.0 is the evolution of Stable Diffusion and the next frontier for generative AI for images. The model is capable of generating images with complex concepts in various art styles, including photorealism, at quality levels that exceed the best image models available today. Like the original Stable Diffusion series, SDXL 1.0 is highly customizable with simpler prompting requirements, true to the intention of the prompts. It also exhibits ability to generate difficult concepts such as hands and text, or spatially arranged objects and persons.
You can now derive the combined advantages of SDXL 1.0 model performance and MLOps controls with SageMaker features such as Pipelines, Debugger, or container logs. The model will be deployed in an AWS secure environment under your VPC controls, helping ensure data security.
SDXL 1.0 is available today in SageMaker JumpStart initially in US East (Ohio), US East (N. Virginia), Europe West, US West (Oregon), Asia Pacific (Tokyo), and Asia Pacific (Sydney), regions. It can be deployed on AWS Inferentia2 instances, optimized for inference tasks, to derive better price and performance results. To get started with SDXL 1.0 via SageMaker JumpStart, see documentation and blog.