
Stability AI Releases 'Stable Doodle', a Sketch-to-Image Tool (techcrunch.com) 11
"Stability AI, the startup behind the image-generating model Stable Diffusion, is launching a new service that turns sketches into images," reports TechCrunch.
Stable Doodle is online now and "free, but subject to limits," according to TechCrunch's article. And their reporter adds that the example images selected by the company to showcase their new technology "looked quite good, at least in comparison to the doodle that inspired them." "Stable Doodle is geared toward both professionals and novices, regardless of their familiarity with AI tools," Stability AI writes in a blog post shared with TechCrunch via email. "With Stable Doodle, anyone with basic drawing skills and online access can generate high-quality original images in seconds..."
In addition to a sketch, Stable Doodle accepts a prompt to guide the image generation process, such as "A comfy chair, 'isometric' style" or "Cat with a jeans jacket, 'digital art' style." There's a limit to the customization, though — at launch, Stable Doodle only supports 14 styles of art.
Stability AI envisions Stable Doodle serving as a tool for designers, illustrators and other professionals to "free up valuable time" and "maximize efficiency" in their work. At the same time, the company cautions that the quality of output images is dependent on the detail of the initial drawing and the descriptiveness of the prompt, as well as the complexity of the scene being depicted. "Ideas drawn as sketches can be immediately implemented into works to create designs for clients, material for presentation decks and websites or even create logos," the company proposes.
Stable Doodle is online now and "free, but subject to limits," according to TechCrunch's article. And their reporter adds that the example images selected by the company to showcase their new technology "looked quite good, at least in comparison to the doodle that inspired them." "Stable Doodle is geared toward both professionals and novices, regardless of their familiarity with AI tools," Stability AI writes in a blog post shared with TechCrunch via email. "With Stable Doodle, anyone with basic drawing skills and online access can generate high-quality original images in seconds..."
In addition to a sketch, Stable Doodle accepts a prompt to guide the image generation process, such as "A comfy chair, 'isometric' style" or "Cat with a jeans jacket, 'digital art' style." There's a limit to the customization, though — at launch, Stable Doodle only supports 14 styles of art.
Stability AI envisions Stable Doodle serving as a tool for designers, illustrators and other professionals to "free up valuable time" and "maximize efficiency" in their work. At the same time, the company cautions that the quality of output images is dependent on the detail of the initial drawing and the descriptiveness of the prompt, as well as the complexity of the scene being depicted. "Ideas drawn as sketches can be immediately implemented into works to create designs for clients, material for presentation decks and websites or even create logos," the company proposes.
Doctor's prescription (Score:4, Interesting)
Can they also develop a language model for reading handwritten doctor's prescriptions?
I once had to program an index program for foreign language document and saw an Arabic doctor's recipe. The only visual difference between an Arabic and a Dutch recipe is made by the small printed characters that make it a real recipe.
As a side note, a friend of mine was the daughter of two doctors. If she was sent to go shopping, she always visited the pharmacist first, so she knew what was on the shopping list.
Re: (Score:2)
In fact, once the prescription has been filled and I haven't arrived before closing time to pick it up, it goes into a 24/7 vending machine with a PIN for the next week.
Life is good, (but don't talk about the delightful weather improvements where I am due to climate change, which is terrible over the long term. I am freaked out about that 'technology'.)
img2img? (Score:4, Interesting)
Just did a quick test and it doesn't seem to be very different from using the img2img functionality with high denoising and some pre-baked styles.
At least it's way more accessible for normal people than running it yourself.
Re: (Score:2)
Re: (Score:2)
Oh, wait.
Re: (Score:3)
Loosely guided (Score:3)
I spent a minute and did a sketch [postimg.cc] with my thumb on my phone.
Any toddler would recognize a primitive smille but this 'net saw a double-chin fold.
Interesting comparison.
Useless. (Score:2)
EmilyWilde (Score:1)