There’s a very easy way, and much more powerful way to create infinite variations of an image. We provide both of these tools.. Let’s get into it.
You have completed Image Uploading Basics and know the difference between Strength and Guidance.
- Create AI variations of any photo
- Create a higher resolution image
- Learn about ControlNet Modes
Step 1: Render an image
I simply typed a simple prompt “close-up image of men’s shoes”
Step 2 – After uploading or rendering the image, click the Tools menu
Click the more button, and the AI will produce many more of the same image.
Tip: Behind the scenes, the AI is assigning a random value to each image called a Seed. A seed isn’t like a photo ID or an item number, it is a tag that allows us to repeat an image should we want to revisit it in the future. The more button is “seed traveling”, increasing the value of that first seed number by a few digits. So the result is variation.
In a previous lesson we covered Remix in the Upload tutorial, and it’s the other quick way to get variations. How about Clown Shoes? In this case, instead of clicking More, click Remix, and enter the word Clown Shoes. It’s as easy as that.
You can go much further, like only using the contours of the image as the basis for the next picture, or using the image as a reference to make something entirely new.
Remix – One of the tools in Stable2go, also known as Img2Img. You are uploading or creating an image first, and then “remixing” it into something new. None of the original pixels are preserved.
More – A number between 0.50 and 20 that tells the AI how strictly to follow the prompt. A low guidance is considered under 7, and high above 12. If you are getting artifacts, lowering guidance helps.
Seed – A random number assigned to a generation. A seed by itself doesn’t mean a specific image, it is more like an anchor. When the exact same prompts, the exact same guidance, samplers, and other settings are used, the same image can be generated by another person on a different computer.
ControlNet – A suite of tools that create image variations, by using an image as an input. You can input a photograph, a pose, a contour, and create variations.