Amazon Launches Upgraded Titan Image Generator v2 AI Model
Amazon on Tuesday announced the launch of its enhanced artificial intelligence (AI) model, Titan Image Generator v2. Following the release of Image Generator v1 last year, the new image generation model offers enhanced capabilities and functionality. Aimed at the tech giant’s enterprise customers, the AI model can generate images using reference images, edit images, remove backgrounds, and be adjusted to maintain brand style and subject consistency. Currently, the Amazon Titan Image Generator v2 is available in limited quantities in select regions in the US.
Amazon Titan Image Generator v2 Features
The company announced the second generation of its enterprise-focused image generation platform in a blog postTo access it, users in eligible regions should go to the Amazon Bedrock console and check model access on the bottom left panel. There, users can request access to the Titan Image Generator G1 v2 AI model.
According to the post, the new model shows a notable upgrade in image conditioning. This feature can generate new images using a reference image and a text prompt. Based on instructions, the generated image can focus on specific visual features such as edges, object outlines, structural elements, and more.
The model supports two types of image conditioning. The 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 offers more granular control over the output, as the user can define specific areas within which the AI model can generate new elements.
For brands looking for a consistent approach to their generated images and adhering to brand colors and design language, the Titan Image Generator v2 offers a color conditioning feature. This allows users to specify the color palette used in the generated images. Users can also add a reference image with the provided hex colors and the AI generated image will implement the style while adhering to the instructed colors.
Additionally, the background removal feature has also received upgrades. The company claims that it can “intelligently detect and segment multiple foreground objects, neatly isolating even complex scenes with overlapping elements.”
The Amazon Titan Image Generator v2 is available in the US East (North Virginia) and US West (Oregon) regions. More regions will be added in future updates.
