article thumbnail

Generating fashion product descriptions by fine-tuning a vision-language model with SageMaker and Amazon Bedrock

AWS Machine Learning - AI

To solve this problem, this post shows you how to predict domain-specific product attributes from product images by fine-tuning a VLM on a fashion dataset using Amazon SageMaker , and then using Amazon Bedrock to generate product descriptions using the predicted attributes as input. For details, see Creating an AWS account.

Fashion 102
article thumbnail

Automate the process to change image backgrounds using Amazon Bedrock and AWS Step Functions

AWS Machine Learning - AI

Many customers, including those in creative advertising, media and entertainment, ecommerce, and fashion, often need to change the background in a large number of images. However, Amazon Bedrock and AWS Step Functions make it straightforward to automate this process at scale. Invokes the Amazon Bedrock InvokeModel API action.

AWS 114
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Demystifying MLOps: From Notebook to ML Application

Xebia

In this blog post, we’ll try to demystify MLOps and take you through the process of going from a notebook to your very own industry-grade ML application. To ensure our code will run on the server, we need to containerize our application. A common open source tool that allows you to containerize your applications is Docker.

article thumbnail

DS Smith sets a single-cloud agenda for sustainability

CIO

Going into full partnership with AWS is much more of a strategic direction for us because using one stack is the most effective way to do that.” Prague-based IDC analyst Jan Burion believes that DS Smith’s consolidation on AWS will increase the company’s ability to achieve its sustainability goals with greater efficiency.

article thumbnail

How Zero Trust is supposed to look

CIO

Zero trust for users Your users need fast, secure, and reliable access to applications and the internet from anywhere and everywhere. virtual machine, container, microservice, application, storage, or cloud resource) used either as needed or in an always-on fashion to complete a specific task; for example, AWS S3.

B2B 222
article thumbnail

LexisNexis rises to the generative AI challenge

CIO

“If you’re an end user and you are part of our conversational search, some of those queries will go to both ChatGPT-4 in Azure as well as Anthropic in AWS in a single transaction,” the CTO says. “If We use AWS and Azure. If I type in a query, it could go to both based on the type of question that you’re asking.

article thumbnail

Automate your workload insights

Xebia

Managing more than one AWS accounts can become challenging. AWS Organizations provides a way to manage many accounts. When you follow the best practices of AWS, you will end up using an account per environment. So stop keeping track of your workloads the old fashion way and start using automation tools. Naming schema?

AWS 130