Stability AI, the startup known for its image-generating model Stable Diffusion, has introduced a new service called Stable Doodle. Leveraging the advanced capabilities of the Stable Diffusion model, Stable Doodle is designed to convert sketches into visually appealing and high-quality images. With its user-friendly approach, this new offering aims to cater to both professionals and novices, enabling anyone with basic drawing skills to create original artwork effortlessly.
Precise Control of Stable Doodle Service Over Sketch-to-image AI Tools
Stable Doodle sets itself apart from other sketch-to-image AI tools by offering a more “precise” level of control during the image generation process. By combining the Stable Diffusion XL model with Tencent’s Applied Research Center’s T2I-Adapter, Stable Doodle allows users to provide sketches as input and guides the model to produce refined and customized output artwork. This unique feature empowers users to have a greater influence on the final results.
“T2I-Adapter enable[s] Stable Doodle to understand the outlines of sketches and generate images based on prompts combined with the outlines defined by the model,” Stability AI explains in the blog post. Stable Doodle represents Stability AI’s pursuit of new revenue sources following a temporary slowdown in its commercial endeavors. Although Stable Doodle is currently offered for free with certain limitations, Stability AI aims to leverage the popularity and adoption of the tool to drive its business growth. The company recently raised $25 million in funding through a convertible note, bringing its total funding to over $125 million as it seeks to expand its operations and solidify its market position.
Enhanced Customization and Limitations
Stable Doodle not only accepts sketches but also incorporates prompts to guide the image generation process. For instance, users can provide prompts like “A comfy chair, ‘isometric’ style” or “Cat with a jeans jacket, ‘digital art’ style.” However, it’s important to note that the current version of Stable Doodle supports a limited set of 14 art styles. The quality of the generated images depends on the initial drawing’s level of detail, the prompt’s descriptiveness, and the depicted scene’s complexity.
Stability AI envisions Stable Doodle as a valuable tool for designers, illustrators, and other professionals, aiming to free up their time and maximize efficiency in their work. The immediate implementation of sketched ideas into designs for clients, presentation materials, websites, and even logos is a significant benefit offered by Stable Doodle. Additionally, Stability AI plans to expand the capabilities of Stable Doodle to cater to specific verticals, such as real estate applications, in the future.
Also read: Tiktok Launches its First AI Text-to-Image Generator for Creators
