Stability AI, the company behind the image-generating AI Stable Diffusion, has this week launched a new tool that will allow you to create images from sketches. Called Stable Doodle, this new service makes use of Stable Diffusion’s latest model to analyze the outline of a sketch and generate a dynamic image from it.
“Stable Doodle is aimed at both professionals and beginners, regardless of their familiarity with AI tools,” Stability AI says in a blog post. “With Stable Doodle, anyone with basic drawing skills and Internet access can generate high-quality original images in a matter of seconds.”
Stable Doodle is powered by a Stable Diffusion model called Stable Diffusion XL, which is combined with a “conditional control solution” developed by Tencent’s Applied Research Center. Called T2I-Adapter, this “control solution” allows Stable Diffusion XL to accept sketches as input and guide the model so that the output illustrations come out as well as possible.
But the image generator tool not only supports sketches as input, but you can also write what you are looking for and with the style you want, in order to make the final result more precise (in English only). Among the images published by Stability AI, we find, for example, a “comfortable chair”, with “isometric style”, one of the 14 styles that can be used at the moment.
Stable Doodle is now available through ClipDrop, a Stability AI platform. A new image generating tool that joins a growing list that includes names such as DALL-E 2, Midjourney or Perfusion, recently launched by Nvidia.
Some of the links added in the article are part of affiliate campaigns and may represent benefits for Softonic.