Introducing Stable Cascade: the new image generation model from the creators of Stable Diffusion

Stability AI, the company behind Stable Diffusion, the industry-leading image generation AI and the foundation of many other text-to-image AI tools, has announced the launch of Stable Cascade, an image generation model that promises to be faster and more powerful than its predecessor.

Stable Diffusion ACCESS

The new model of Stability AI can generate photos and provide variations of the exact image it has created, or attempt to increase the resolution of an existing photo. Other text-to-image editing functions include “inpainting” and “outpainting”, where the model will only fill in a specific part of the image, as well as “canny edge”, where users can take a new photo using only the edges of an existing image.

The new model is available on GitHub for researchers, but not for commercial use, and it offers more options even when companies like Google and even Apple are releasing their own image generation models.

Stable Diffusion ACCESS

Stability AI helped popularize the “stable diffusion” method and has also been the subject of several lawsuits alleging that Stable Diffusion was formed using copyrighted data without permission from the rights holders (a trial for one of Getty Images’ lawsuits against Stability AI is scheduled to take place in December in the UK).

Unleashing the Power of AI: AI Stable Diffusion’s Latest Service Holds Immense Promise

This is how Stable Doodle works, the new Stability AI tool with which you can quickly create an image from a simple sketch.

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 diffusion ACCESS

“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.

“adorable owl” with origami style – Stability AI

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 diffusion ACCESS

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.