Overview
This solution is offered in the form of an EC2 AMI, with Stable Diffusion Webui pre-installed (including the AWS SageMaker Extension).
You will need to manually deploy the AWS backend service suite to support the AWS SageMaker Extension (including APIGateway, Lambda, DynamoDB, SageMaker Endpoint, etc.). Please visit: https://github.com/awslabs/stable-diffusion-aws-extension , or contact eCloudrover for technical support.
SD-Webui: This part is provided by EC2 AMI , with Ubuntu 20.04 as the underlying operating system. It has Stable Diffusion WebUI installed, as well as Stable Diffusion 1.5 and ControlNet models integrated. Nginx application is deployed to forward requests from port 80 to Stable Diffusion WebUI's port 7860. Both Nginx and SD-WebUI are configured to automatically start at boot.
AWS SageMaker Extension: This is an SD-WebUI extension that helps users migrate existing workloads (inference, training, ckpt merging, etc.) from local servers or standalone EC2 instances to the AWS cloud environment.
Highlights
- One-click subscription and one-click start, quickly build a Stable Diffusion environment on the cloud without complicated configuration processes.
- Flexible scalability of computing power enables asynchronous inference and parallel training, improving AIGC production efficiency.
- Powerful task management system saves all inference and training content, supporting nearly unlimited storage space and extremely low-latency access.
Details
Typical total price
$1.752/hour
Pricing
Free trial
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
|---|---|---|---|
p3.2xlarge | $1.00 | $3.06 | $4.06 |
p3.8xlarge | $1.00 | $12.24 | $13.24 |
p3.16xlarge | $1.00 | $24.48 | $25.48 |
p3dn.24xlarge | $1.00 | $31.212 | $32.212 |
g4dn.xlarge | $1.00 | $0.526 | $1.526 |
g4dn.2xlarge Recommended | $1.00 | $0.752 | $1.752 |
g4dn.4xlarge | $1.00 | $1.204 | $2.204 |
g4dn.8xlarge | $1.00 | $2.176 | $3.176 |
g4dn.12xlarge | $1.00 | $3.912 | $4.912 |
g4dn.16xlarge | $1.00 | $4.352 | $5.352 |
Additional AWS infrastructure costs
Type | Cost |
|---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
No refund. If you have any product questions, please refer to the solution manual. Or get in touch with us at Solution-Support@ecloudrover.com .
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
The solution is based on Stable Diffusion, integrated with AWS SageMaker, and can fully decouple components such as model storage, inference tasks and training tasks, and flexibly expand computing power. Also prepared built-in plugins for model management, history management, model training, high-level graph control, and other potential usage requirements, making it easier for advanced users to use.
Additional details
Usage instructions
The following is a step-by-step guide on how to start an EC2 instance to run the Stable Diffusion WebUI service after subscribing to the AMI:
-
Navigate to the MarketPlace Subscription page, find the "Stable Diffusion Webui with ControlNet - eCloudrover" subscription and click the "Launch new instance" button below.
-
On the Launch new instance page, make sure the Region is the one you need, and click "Continue to launch through EC2".
-
In the Launch an instance interface, pay attention to the following parameters:
3.1. Instance type: g4dn.xlarge is the minimum requirement, and we recommend using g4dn.2xlarge or g5.2xlarge or higher;
3.2. Key pair: If you need to use an SSH client to connect to the server for operation and maintenance, you must specify a Kay pair;
3.3. Auto-assign public IP: Please edit "Networking settings" and select "Auto-assign public IP" as "Enable";
3.4. Firewall (security groups): Please keep port 80 open; if you need to use an SSH client to connect to the server for operation and maintenance, you also need to keep port 22 open; 3.5. Configure storage: We recommend that you choose a gp3 Root volume of 100 GB or more.
-
After configuring, click "Launch instance". When the "Instance state" of the EC2 instance displays "Running", you can access the Public IP of the EC2 instance. (Please note to use Http access, Https will display "ERR_CONNECTION_CLOSED")
-
You will be prompted to enter a username and password to log in to the Webui. The username is "webui" and the password is the Instance ID of the EC2 server.
-
If you see "AIGC WebUI service starting... It takes some time to start up for the first time" when you access the Public IP, please wait patiently for 10-15 minutes. The first startup of the server requires waiting for the Stable Diffusion environment configuration and model loading.
Resources
Vendor resources
Support
Vendor support
Service support telephone: +86 400-002-0885 Service support email: Solution-Support@ecloudrover.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
