bt_bb_section_bottom_section_coverage_image

Amazon Titan Image Generator v2 AI Model Launched With Improved Image Conditioning Feature

On Tuesday Amazon introduced its artificial intelligence (AI) model, the Titan Image Generator v2. After the release of Image Generator v1 last year, the new image generator model has been improved in power and performance. Aimed at the tech giant’s business customers, the AI ​​model can generate images using reference images, edit images, remove backgrounds and ensure that the brand image is maintained and consistency of program. Currently, Amazon Titan Image Generator v2 is available on a limited basis in select regions of the United States.

Amazon Titan Image Generator v2 Features
The company announced the second generation of its enterprise-focused image generator in a blog post. To access, users in eligible regions must go to the Amazon Bedrock dashboard and check the template availability in the lower left corner. There, users can request access to the Titan Image Generator G1 v2 AI model.

According to the announcement, the new model features significant improvements in image processing. This function can generate a new image using a reference image and a text message. Depending on the guidelines, the generated image can focus on specific visual features such as edges, object parts, structure parts, etc.

The model supports two types of image conditioning. First is Canny edge, which can “extract the prominent edges within the reference image, creating a map that the Amazon Titan Image Generator can then use to guide the generation process.” The second is called segmentation which provides a more granular control over the output as the user can define specific areas within which the AI model can generate new elements.

For brands seeking a consistent approach to their generated images and adherence to the brand colours and design language, the Titan Image Generator v2 offers a colour conditioning feature. Using this, users can specify the colour palette which will be used in the generated images. Users can also add a reference image with the provided hex colours and the AI-generated image will implement the style while adhering to the instructed colours.

In addition to this, the background removal feature has been improved. The company claims it can “intelligently detect and segment objects in the past, ensuring that complex features and overlapping elements are clearly separated.”

Amazon Titan Image Generator v2 is available in US East (N. Virginia) and US West (Oregon). More regions will be added through future updates.

Share
× WhatsApp