Stable Doodle is an AI image generator that works by combining a user’s drawing with a text prompt.
brought to you by AI stabilityStable Diffusion, the makers of Stable Diffusion, is a free drawing-to-image tool that can turn simple graphics into complex designs.
What is Stable Doodle?
Launched in mid-July 2023, Stable Doodle is geared towards both professionals and beginners and has received positive reviews. It is similar to others AI image makers in the market like Medjourney But instead of only accepting text prompts from its users, it also comes with a drawing board.
“Ideas drawn as graphics can be immediately implemented in the works to create designs for clients, materials for presentation decks and websites, or even create logos,” the company said in a statement. Blog.
This free online tool works by combining Stable Diffusion XL’s advanced image generation technology from Stability AI’s Stable Diffusion XL with the powerful T2I transducer. The latter is a tool that text-to-image generators can use to provide them with additional guidance.
It is available on Clipdrop by Stability AI website and as a mobile app (iOS And google apps).
How to use Stable Doodle
Using stable doodles is easier said than done. Simply draw a graphic, add vector text, and hit create. Well, maybe it’s not that hard to explain.
The point is that despite the complexity of what Stable Doodle can accomplish, it is definitely one of the easiest AI tools to use. You don’t even need to sign up for an account to use the basic version. Here’s what you need to do:
1. Visit the website
First, head over to the Stable Doodle website by Stable Doodle following this link. There is no registration required to get started, you can just start messing around.
However, you will only get 1 fee per hour (maximum of 12) as an anonymous user. If you want more, you will need to create a free account.
2. Start drawing
Start drawing your scene with the Pen Tool. This can include animals, objects, landscapes, and people. For the best results, it’s best to stick to just one of these categories as a focal point. Eraser tool is also at your disposal.
At the time of this writing, it was not possible to import graphics that were viewed outside of the Stable Doodle website. However, the company expects to add this feature in the future. For now, you’ll have to use a mouse, trackpad, or stylus for this part.
It’s possible to skip the drawing part and go straight to adding a text prompt, as shown in the next step.
3. Write prompt text
Before you can get your hands on your masterpiece, you’ll need to include a text message. In this prompt, you’ll want to describe in a few words what the graphic is meant to represent.
One of the claims recommended by Stable Doodle is simply “living room”. So, unlike the case in artificial intelligence tools like chat Where you are encouraged to add as much detail as possible in your claims, just a short description will do here.
However, if you’re looking for something specific, you can add several lines of text to direct the AI.
4. Select the style
As part of your prompt, you can select the style you want the AI to give your doodles – Picasso-style, cyberpunk, or realism are all possibilities.
If you’re not feeling particularly eclectic, there’s also a “no pattern” option you can use. You can continue without choosing a style or select another style from the 14 available preset style options. These include origami, anime and pixel art.
5. Press “Create”
After your drawing is up and ready, it’s time to hit the “Create” button. If all goes well, Stable Doodle should present you with a grid of 3 different AI-generated versions of art based on your initial drawing along with your quick and style selection.
6. Download it
Select your favorite photo and download it. Using the free version of Stable Doodle means there will be a watermark at the bottom right of your image.
As we mentioned at the beginning, without an account as an anonymous user, you can only create 12 images per 24 hours. Signing up for a free account should increase that limit significantly.
The stable doodle is awesome pic.twitter.com/DAKyYQ3drGJuly 17, 2023
I tried it – here’s what happened
I tested Stable Doodle in two different ways which I thought seemed fair.
First, I would try to create an inanimate object while giving as much space as possible for the AI to be creative. If I’m someone who can’t draw to save their life (I happen to be such a person), I’m going to need all the help I can get to end up with something cool.
Then, finally, I’ll try to draw a widely known person and ask the AI to be as realistic as possible. I wanted to see how well a stable spread could stick to creating exactly what I wanted rather than resorting to some kind of AI image bank. In the future, Stable Doodle should allow user-entered images. If I upload a picture of myself with my friends, I want us to still be recognizable after Stable Diffusion is fixed.
First, inanimate objects. What better way to test an AI’s creativity than to ask it to invent something that doesn’t exist? I used the following prompt:
“A futuristic device from the year 3000 that uses technology never seen before. It consists of a display on top of a hovering desk with a space-time shifter at the bottom. Drawn in the style of a Borderlands game.”
I think we still love the square or the rectangle Displays In the future that’s what I drew. I came out on a tip with a triangle in it like a desk. Reserve your judgment on my space-time-altering machine for the next millennium.
The results look great! The first image in the upper right of the grid seems to do the trick. It has a hover screen complete with a futuristic AI interpretation of something that could change our universe. I’m not sure if extended time travel is possible with the second device, but the graphic in the bottom right again has some potential.
Whether Stable Doodle has succeeded in imitating Borderlands’ role-playing style is subjective. After all, discussions are about what kind of art is used in it Borderlands The same has been heated in the past. However, Grid’s visuals definitely look like hand-drawn pieces that wouldn’t look out of place in a graphic novel, which is what the game designers were going for.
Let’s not forget that we started with my three poorly drawn figures. I guess we can call this a win for Stable Doodle.
It’s time for the final test. Can a stable doodle creatively portray a person while ensuring that they are still recognizable by the end of the process? A familiar face would make it easier to judge, so I thought of an American pop star Taylor Swift who has, as of this month, more No. 1 albums than any woman in history.
If I simply wanted a picture of Taylor Swift, I’d just text. Without adding a little drawing, there’s no use for the Stable Doodle drawing board. So I drew a weird looking stringed instrument but left it to the AI to try and figure out what it was supposed to be.
A quick read, “Taylor Swift holds a musical instrument in her right hand. The instrument is made of silver. Painted in the Mona Lisa style.”
Results have been mixed. Swift seemed to be herself but adding the machine how and where I wanted was something Stable Doodle couldn’t do yet. My request to have the drawings resemble Leonardo da Vinci’s Mona Lisa, except for some resemblance to Swift’s pose in the bottom left image, was also denied.
Was it a Da Vinci problem? I tried again to order the same thing but in the style of Johannes Vermeer, creator of Girl with a Pearl Earring. While there was a slight improvement in terms of design, the wonky machines persevered.
Stable doodles are great. It’s even better if you draw well. As someone with poor drawing skills, the results depended heavily on my text prompts. Once I can load and change externally generated images, I think I’ll be able to use Stable Doodle to its fullest extent. However, letting me add a small sketch made the AI-generated images feel a bit more personal, particularly in the first test which preserved the concept of the shapes I drew.
For the artistically gifted, Stable Doodle is ready and ready to add the finishing touches to your work or add that spark to a quick drawing. if I were Cameraman By working on some conceptual technical examples for the client, you can sketch out your blueprint and free up some of your valuable time by letting the AI finish the piece.
If you haven’t already, I recommend giving Stable Doodle a whirl and letting your creative juices flow. In the words of Stability AI: The possibilities are endless and it’s so much fun!
More Tom’s guide
[ad_2]