Do it with a doodle: AI tool "Stable Doodle"
There are AI tools that require an explanatory text to create an image. "Stable Doodle" is a tool that generates new images from a quick sketch.
A picture is worth a thousand words. While with other image generators you have to struggle with long explanations to get a usable result, the new AI tool "Stable Doodle" uses your sketch.
In 2022, Stability AI published the programme Stable Diffusion. It became famous thanks to the Lensa app, which allows you to create new pictures of yourself from selfies. I tried it out myself for my cover picture for an AI article.
The creators have now released a new version of the tool. In contrast to Stable Diffusion, you can not only enter text in Stable Doodle, but also create a sketch.
The interface is kept simple: You get a white field into which you scribble with your cursor.
Eraser and back arrow are available for errors. Then describe the content of your doodle in one sentence and choose a style as desired. From realistic and comic to origami and pixel art, there are plenty of options.
Source: Michelle Brändle
Finally, click on the Generate button and you will receive three outputs. These can be downloaded, albeit with a watermark. In my case, I think it's worth noting that the proportions of my sketch are maintained. Otherwise, the images look pretty funny.
Source: Michelle Brändle
Source: Michelle Brändle
However, its use is limited. After a few attempts with the tool, Stable Doodle wants me to create an account with an email address - or I wait a day and can then have images created again.
Stable Doodle is not the only tool that uses sketches as input. Even simpler, but with the same concept, Scribble Diffusion works, for example. Here too, the results are more fun than really good due to the adherence to the proportions of my sketches.
Source: Michelle Brändle
Source: Michelle Brändle
With Animated Drawings you can create an animation based on a character sketch. This works by uploading your drawing under certain conditions. There you also define where the arms, legs and head are.
But be warned: by uploading your images, you are giving the companies using these public tools permission to use them for their databases. This is how you train the AI with your own works and ideas.
Cover photo: Michelle Brändle16 people like this article
In my world, Super Mario chases Stormtroopers with a unicorn and Harley Quinn mixes cocktails for Eddie and Peter at the beach bar. Wherever I can live out my creativity, my fingers tingle. Or maybe it's because nothing flows through my veins but chocolate, glitter and coffee.