Extension for Stable Diffusion on Amazon Web Services

Unlock the Power of Generative AI in the Cloud with Ease and Speed

Extension for Stable Diffusion on Amazon Web Services

Unlock the Power of Generative AI in the Cloud with Ease and Speed

Overview

The Extension for Stable Diffusion on Amazon Web Services solution helps customers migrate their existing Stable Diffusion model training, inference, and finetuning workloads from on-premises servers to Amazon SageMaker using extension and CloudFormation template. By leveraging elastic resources in the cloud, it accelerates model iteration and avoids performance bottlenecks associated with single-server deployments.

Benefits

Convenient Installation

This solution leverages CloudFormation for easy deployment of Amazon Web Services middleware. Combined with the installation of the native Stable Diffusion WebUI (WebUI) features and third-party extensions, users can quickly utilize Amazon SageMaker's cloud resources for inference, training and finetuning tasks.

Convenient Installation

This solution leverages CloudFormation for easy deployment of Amazon Web Services middleware. Combined with the installation of the native Stable Diffusion WebUI (WebUI) features and third-party extensions, users can quickly utilize Amazon SageMaker's cloud resources for inference, training and finetuning tasks.

Community Native

This solution is implemented as an extension, allowing users to seamlessly use their existing WebUI without any changes. Additionally, the solution's code is open source and follows a non-intrusive design, enabling users to keep up with community-related feature iterations, such as popular plugins like Dreambooth, ControlNet, and LoRa.

Community Native

This solution is implemented as an extension, allowing users to seamlessly use their existing WebUI without any changes. Additionally, the solution's code is open source and follows a non-intrusive design, enabling users to keep up with community-related feature iterations, such as popular plugins like Dreambooth, ControlNet, and LoRa.

High Scalability

This solution decouples the WebUI interface from the backend, allowing the WebUI to launch on supported terminals without GPU restrictions. Existing training, inference, and other tasks can be migrated to Amazon SageMaker through the provided extension functionalities, providing users with elastic computing resources, cost reduction, flexibility, and scalability.

High Scalability

This solution decouples the WebUI interface from the backend, allowing the WebUI to launch on supported terminals without GPU restrictions. Existing training, inference, and other tasks can be migrated to Amazon SageMaker through the provided extension functionalities, providing users with elastic computing resources, cost reduction, flexibility, and scalability.

Technical details

The diagram below presents the architecture you can automatically deploy using the solution's implementation guide and accompanying Amazon CloudFormation template.

架构图

1. Users in WebUI console will trigger the requests to API Gateway with assigned API token for authentication. Note that no Amazon Web Services credentials are required from WebUI perspective.

2. Amazon API Gateway will route the requests based on URL prefix to different functional Lambda to implement util jobs (for example, model upload, checkpoint merge), model training and model inferencing. In the meantime, Amazon Lambda will record the operation metadata into Amazon DynamoDB (for example, inferencing parameters, model name) for successive query and association.

3. For training process, the Amazon Step Functions will be invoked to orchestrate the training process including Amazon SageMaker for training and SNS for training status notification.
For inference process, Amazon Lambda will invoke the Amazon SageMaker to implement async inference. Training data, model and checkpoint will be stored in Amazon S3 bucket delimited with difference prefix.

AI Solution Kit

One stop to find various AI solutions for common use cases, AI Solution Kit provides a series of out-of-the-box AI features on the cloud, such as Optical Character Recognition (OCR), general object recognition, face detection, text similarity, image similarity, and car license plate.

Machine Learning

Build with powerful services and platforms, and the broadest machine learning framework support anywhere.

Amazon Web Services Solutions

Explore the Amazon Web Services solutions library.

Use cases for this Amazon Web Services Solution
Machine Learning
About this deployment
Version
1.5.0

Released
03/2024

Author
Amazon Web Services

Est. deployment time
10 mins
Source code CloudFormation template link
Deployment options
Ready to get started?
Ready to get started?

Deploy this solution by launching it in your Amazon Web Services Console
探索所有亚马逊云科技解决方案
Explore all Amazon Web Services Solutions

Browse our portfolio of Amazon Web Services -built solutions to common architectural problems.

Learn more 
查找合作伙伴
Find a Partner

Find Amazon Web Services certified consulting and technology partners to help you get started.

Learn more 
开始在控制台中构建
Start building in the console

Sign-up and start exploring our services.

Get started