Overview
Create musical compositions using generative AI tools with this virtual machine image optimized for NVIDIA GPUs. Mindgrub Technologies, in partnership with the Baltimore Symphony Orchestra, used the tools available in this image to present "AI in A Minor," an event featuring AI-generated compositions being performed live by BSO musicians.
With this AMI, you can launch a GPU-accelerated EC2 VM instance in minutes with a pre-installed Ubuntu OS, GPU driver, Docker, and FFmpeg. This AMI also contains the Riffusion and Anticipation tools, both able to leverage NVIDIA CUDA. Finally, we included the following Hugging Face models: stanford-crfm/music-small-800k, stanford-crfm/music-medium-800k, and riffusion/riffusion-model-v1.
Once your instance launches, you can immediately use one of these preinstalled tools to experiment with music created by generative AI.
Highlights
- Includes Riffusion (a library for real-time music and audio generation with stable diffusion) and FFmpeg (a library to record, convert and stream audio and video).
- Includes Anticipation (a library for creating anticipatory training datasets, and for sampling from models trained with anticipation).
- Built on top of the official AWS Deep Learning Base AMI for Ubuntu 20.04 (Focal).
Details
Typical total price
$0.526/hour
Features and programs
Financing for AWS Marketplace purchases
Pricing
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
|---|---|---|---|
p3.2xlarge | $0.00 | $3.06 | $3.06 |
p3.8xlarge | $0.00 | $12.24 | $12.24 |
p3.16xlarge | $0.00 | $24.48 | $24.48 |
p3dn.24xlarge | $0.00 | $31.212 | $31.212 |
p4d.24xlarge | $0.00 | $32.773 | $32.773 |
g4dn.xlarge Recommended | $0.00 | $0.526 | $0.526 |
g4dn.2xlarge | $0.00 | $0.752 | $0.752 |
g4dn.4xlarge | $0.00 | $1.204 | $1.204 |
g4dn.8xlarge | $0.00 | $2.176 | $2.176 |
g4dn.12xlarge | $0.00 | $3.912 | $3.912 |
Additional AWS infrastructure costs
Type | Cost |
|---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
This AMI is provided free of charge.
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
Initial release
Additional details
Usage instructions
The /opt/ai directory contains the Riffusion and Anticipation tools. This is the home directory for the "aiuser" user.
Switch to the "aiuser" user, which has three pre-trained models from Hugging Face saved in /opt/ai/.cache
You can work with Riffusion by activating its Python virtual environment: "source /opt/ai/riffusion/.venv/bin/activate"
You can work with Anticipation by activating its Python virtual environment: "source /opt/ai/anticipation/.venv/bin/activate"
Support
Vendor support
Email us for assistance with this virtual machine image: opensource@mindgrub.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.