Use Amazon Titan models for image generation, editing, and searching
Machine Learning Blog
This blog post introduces two new AI services from Amazon - Amazon Titan Image Generator and Amazon Titan Multimodal Embeddings.
Specifically, the article covers:
- Using Amazon Titan Image Generator for image generation from text prompts, iterating on generated images, editing existing images by adding/removing objects, and changing backgrounds
- Using Amazon Titan Multimodal Embeddings for converting text and images into semantic vectors to enable accurate search and recommendations
- Code examples in Python demonstrating how to use these services
- A case study using a synthetic e-commerce dataset with images generated by Titan Image Generator and indexed/searched using Titan Multimodal Embeddings
- Conclusion highlighting the potential applications of these new AI services and the resources provided
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Mar 27
2024
2024
Fine-tune your Amazon Titan Image Generator G1 model using Amazon Bedrock model customization
Aug 6
2024
2024
Amazon Titan Image Generator v2 is now available in Amazon Bedrock
Apr 23
2024
2024
Amazon Titan Image Generator and watermark detection API are now available in Amazon Bedrock
Dec 20
2024
2024
Generating and editing AI images using Amazon Lightsail for Research
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.