Overview
Withywindle Stable Diffusion WebUI enables users to launch a GPU optimized EC2 instance and use Stable Diffusion models to generate new images and train new models from existing images.
The image includes the Dreambooth extension and a vae-ft-mse checkpoint as well as a variety of popular StableDiffusion models. All StableDiffusion models licensed for use under https://huggingface.co/spaces/CompVis/stable-diffusion-license .
Highlights
- Generate AI images from a text prompt
- Train custom AI models from your own data
- Upscale and modify existing images with AI
Details
Typical total price
$1.312/hour
Pricing
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
---|---|---|---|
g3s.xlarge | $0.08 | $0.75 | $0.83 |
g5.2xlarge Recommended | $0.10 | $1.212 | $1.312 |
g5.4xlarge | $0.12 | $1.624 | $1.744 |
g5.8xlarge | $0.16 | $2.448 | $2.608 |
g5.16xlarge | $0.18 | $4.096 | $4.276 |
Additional AWS infrastructure costs
Type | Cost |
---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
No Refunds
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
- Updated Automatic111 WebUI
Additional details
Usage instructions
This image consists of an Ubuntu server with a recent build of AUTOMATIC111 Stable Diffusion WebUI and a small assortment of AI models.
The WebUI will automatically run on port 7860 of the launched instance. The WebUI may take 10-20 minutes to become available as the large models are copied into memory from freshly created EBS.
SSH runs on port 22 and the login user is "ubuntu". The default security group configuration only allows port 22 ingress.
We recommend that you configure secure access to the WebUI by taking the following steps:
- Configure a DNS record for your instance, either through AWS Route53 or another provider
- Configure the instance security group to allow 0.0.0.0/0 ingress on port 80. (WebUI is not yet routed from port 80 and Nginx will display a default page.)
- SSH to the instance and execute the shell script found at '/home/ubuntu/bin/certbot-init.sh yoursubdomain.example.com'. Make sure to include the DNS record that you have created as an argument and not 'example.com'.
You can also provide your DNS name in the instance user-data in order to configure HTTPS at instance launch time. Make sure to include the DNS record that you have created as an argument and not 'example.com'.
https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html#user-data-view-change
----EXAMPLE-USERDATA----
#cloud-config runcmd:
- [ sh, -c, "/home/ubuntu/bin/certbot-init.sh subdomain.example.com" ]
----EXAMPLE-USERDATA----
- Modify the instance security group rules to allow ingress on port 80, 443 and 22 and only allow your IP or network. We do not recommend that you make the WebUI available to the public Internet by allowing 0.0.0.0/0.
Once HTTPS is configured and the security group is modified, the Stable Diffusion webUI will be available at your domain:
https://<subdomain.example.com>/
The web interface is authenticated. Your username is 'sd_webui' and the password is the same as the instance-id. You can find the instance-id in the EC2 Console or by connecting to the instance over SSH and running 'ec2metadata --instance-id'.
Note: We recommend that you disable 'Advanced Tracking Protection' and 'Duck Duck Go Privacy Essentials' browser extensions as they interfere with the function of the WebUI.
Additional Usage Notes can be found at https://www.withywindlefarms.com/stablediffusion_webui_usage.html
Resources
Vendor resources
Support
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.