Note: Stable diffusion requires a lot of processing, so a GPU instance is recommended. If you want to use a CPU instance due to the high price of GPU instances, you should use instances with higher CPU.
Please note that GPU's are not available in some zones and for some instance types.

Below are the recommended VM configuration requirements:
GPU VM: g4dn.xlarge
CPU VM: t2.xlarge
For CPU, its the minimum specifications but more CPUs are preferred.

Note: GPU instance will perform 10 times or more faster when processing request compared to CPU instance . Typical GPU instance will take few seconds to render the images compared to 7-10 minutes by CPU instance, hence GPU instances are preferred.

Note: This is Stable Diffusion VM offer. If you are looking for a SaaS subscription with hourly pricing without
managing a VM, please visit - https://aws.amazon.com/marketplace/pp/prodview-qj2mhlfj7cx42

Stable Diffusion is open sourced State of the Art text to image AI model. It generates detailed images based on the given text prompts along with other capabilities such as inpainting, outpainting, and generating image-to-image translations. These capabilities along with its open-source nature makes it the best choice for creating AI Arts as compared to other closed source options available.

This VM comes with out of box setup for Stable Diffusion along with an InvokeAI Web Interface . Having your own VM instead of using Stable Diffusion SaaS services will provide you :

• Full control of Stable Diffusion capabilities & how it is utilized for your specific requirements
• Have single VM & its Web UI & setup accessible to multiple users & teams making it more cost effective
• Full ownership of the images & data generated
• Ability to use any model of choice
• Ability to customize Stable Diffusion as per your need

• An intuitive web interface accessible from anywhere to exploit all Stable Diffusion capabilities using a browser
• Original txt2img and img2img modes
• Interactive Command Line Interface
• Outpainting - to extends the original image and inpaints the created empty space
• Inpainting
• Color Sketch
• Prompt Blending
• Loopback, run img2img processing multiple time
• One click install and run script and lot more.