Amazon has made the Amazon Titan Image Generator v2 model generally available to AWS customers using Amazon Bedrock. The improved v2 model allows creation using reference images (called “image conditioning”) and also allows editing capabilities, background removal, iteration and customization, with a focus on maintaining brand style and subject consistency. The new version “can intelligently detect and segment multiple foreground objects,” according to AWS cloud developer Channy Yun. “With the Titan Image Generator v2, you can generate color-conditioned images based on a color palette [and] use the image conditioning feature to shape your creations.”

“Titan Image Generator v2 supports image conditioning, optionally taking in a reference image and focusing on specific visual characteristics in that image, like edges, object outlines and structural elements,” writes TechCrunch. The reference image can be used in conjunction with text prompts.

The new image generator supports two types of image conditioning, canny edge and segmentation,” Yun explains in a blog post:

• The Canny edge algorithm is used to 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. You can “draw” the foundations of your desired image, and the model will then fill in the details, textures, and final aesthetic based on your guidance.
• Segmentation provides an even more granular level of control. By supplying the reference image, you can define specific areas or objects within the image and instruct the Amazon Titan Image Generator to generate content that aligns with those defined regions. You can precisely control the placement and rendering of characters, objects, and other key elements.
  

The image conditioning tool can “detect and segment out specific parts of an image in order to offer new suggestions or possibilities, allowing users to ‘guide’ the creation of an image like never before,” writes TechRadar, pointing out that “the company says its new model can be particularly useful for generating marketing or advertising campaigns, allowing for a range of options or evolutions of a particular image to be created and evaluated.”

Color palette control is among the “standout additions” in the new release, according to Maginative.

Noting that Amazon has said in the past that its models are “trained on a combination of public and private data,” TechCrunch points out that “AWS offers an indemnification policy that covers customers in the event a Titan model like Titan Image Generator v2 regurgitates (i.e. spits out a mirror copy of) a potentially copyrighted training example.”