Recently I had the opportunity to work on an interesting tutorial for Seqera Labs, explaining how to adapt a machine learning inference pipeline to use an AWS Batch GPU environment provisioned using Nextflow Tower.

The example uses Stable Diffusion – an open source text to image model to generate a variable number of images and assemble them into a mosaic. The working pipeline is available here: https://github.com/GJSissons/stable-diffusion-nf

---