Getting started with AWS DeepComposer

When you use the AWS DeepComposer Music studio experiences, your creativity and and generative AI can come together. To start using AWS DeepComposer, you need a trained model and an input track. You can use AWS DeepComposer to train custom models, or you can use sample models. For your input track, you can use a sample input track, record a custom input track, or import a track.

To create a composition, AWS DeepComposer performs inference with a trained model and an input track. After you create your first few compositions, you can start modifying the hyperparameters available in the AWS DeepComposer Music studio to learn more about how generative AI works.

Right now, you can experiment with creating music in the new remixed music studio experience or continue using the classic music studio experience.

In the following topics, you can learn how to use both classic and remixed music studio experiences to perform inference using different generative AI techniques.

You can also train a custom model in the AWS DeepComposer console using a supported generative AI technique. Then, you can use it in the AWS DeepComposer Music studio to generate compositions.

AWS DeepComposer supports training custom models using the generative adversarial networks (GANs) technique. You can train a model that uses either the MuseGAN or the U-Net algorithm.

If you are new to machine learning or generative AI, see learning the basics of generative AI to get started. If you want a deeper dive into the different generative AI techniques supported by AWS DeepComposer, the learning capsules provide an introduction.

After you've created your AWS account, sign in to the AWS DeepComposer console with your AWS account or user credentials. The following exercises assume you've signed in to the AWS DeepComposer console.