Machine Learning

We have only started to see is how Stable Diffusion will get incorporated into existing and greenfield creative workflows. And this will be an exciting step in the evolution of AI-powered tools over the next months and years. DreamCanvas is an exploration of this space built with Blueprint.

Michael Feldstein

March 1, 2023

Blueprint works great for building user-facing applications with fine-tuned models. One popular type of app using fine-tuning is AI avatar generation apps. This project implements a simple version of an avatar generation app like Lensa using Blueprint.

Tuhin Srivastava

February 27, 2023

As soon as I saw Whisper — OpenAI’s open-source model for automatic speech recognition — I knew I had to start experimenting with it. In this blog post, I’ll first show you how you can deploy Whisper instantly as a pre-trained model, then walk you through the steps I took to package and deploy it.

Justin Yi

October 18, 2022

Use Truss to get your model out of a Kaggle notebook and into production in minutes with this quick tutorial!

Jesse Mostipak

September 20, 2022

BentoML and Truss are two open-source frameworks for serving and deploying machine learning models. This article presents a technical comparison of the two open-source frameworks to help you decide which one to use to serve your model.

Philip Kiely

September 15, 2022

Stable Diffusion is an open-source image generation model developed by Stability AI. I wanted to give Stable Diffusion a try, so I set out to deploy it to Baseten. If you’re curious about the process of deploying a cutting-edge model on Baseten, read on and I’ll walk you through the process.

Abu Qader

September 1, 2022

Meet Daniel, Data Scientist and founding data science team member at SIL.

Derek Kim

August 30, 2022

Meet Nikhil, Machine Learning Engineer at Patreon and early data team expert.

Derek Kim

August 9, 2022

Model serving should be a commodity, a standardized process from model to model and environment to environment. But it isn’t. To address this problem, we built Truss. Truss bridges the gap between model development and model deployment.

Phil Howes

August 5, 2022

Our technical writer Philip Kiely walks through four tasks in his content creation process and the models that could accelerate that work and improve its outcomes.

Philip Kiely

June 2, 2022

We sit down with DJ Patil to hear about his path to becoming the first U.S. Chief Data Scientist, and how he applies curiosity to identify the most impactful opportunities for data.

Tuhin Srivastava

May 10, 2022

When you deploy a model on Baseten, you can already invoke it via an API right away. But for production-ready use cases, you often need to wrap model invocation in parsing and business logic for the model to be useful.

Philip Kiely

April 22, 2022

Restore old family photos using our photo restoration app, built with BaseTen and powered by the GFP-GAN model.

Phil Howes

December 23, 2021

Learn how a pre-trained model zoo model, wav2vec, was incorporated into a user-facing audio transcription application, currently being used by the content moderation team at a large consumer tech startup.

Pankaj Gupta

December 13, 2021

Working closely with users in our closed beta, we’ve repeatedly heard that users need to label data to train their models, often before they even have a model. Baseten helps here too! Data scientists can use Baseten to quickly build an API and craft UI for a user-facing data-labeling app...

Amir Haghighat

November 11, 2021

Baseten supports deploying most types of machine learning models; in this post, we’ll go over deploying a simple fast.ai model.

Alex Gillmor

October 27, 2021