Stability AI has unveiled its latest text-to-image model, Stable Diffusion XL 1.0, marking a significant leap in its image-generating capabilities.

The new model promises more vibrant and accurate colors, improved contrast, lighting, and shadows compared to its predecessors. Generating images in 1-megapixel resolution now also takes mere seconds.

Stability AI Launches Stable Doodle That Turns Sketches into Images
Anyone interested can try out Stable Doodle on the ClipDrop platform, owned by Stability AI. The interface is user-friendly and compatible with both desktop and mobile browsers. Users can draw using their finger, mouse, touchpad, or graphics tablet.

The model is accessible through Stability AI's API, Github page, and consumer applications such as ClipDrop and DreamStudio. It will also be featured on Amazon Bedrock, Amazon's cloud platform for hosting generative AI models.

However, it raises ethical concerns, as open source access allows the potential misuse of the model for generating harmful content, like nonconsensual deepfakes. Stability AI assures they have taken measures to mitigate harmful content generation and respect artists' requests regarding their artwork used for training.