Text to image - Walkthrough

Welcome to the very basics of AI image generation. This is where many services stop, but where our work just begins. Text-to-image generation means you enter a description of what you want to see into a text field (this is called your “prompt”). Then hit create and wait for your machine to visualize exactly what you had in mind.

The Process

This tutorial could, of course, end here as there is nothing more to say about that.

However, there is a lot more to explore because no machine can perfectly understand your needs just from your words. We provide various options to influence the generation before hitting the “create” button.

You may have seen the image of the tree before, but it is necessary to understand what happens here. You have influence over every step up to the final output (in other words: your picture).

Choosing a Model

First, choose a model that matches the style you want to achieve. If you want to learn more about models, read our “train your own model” and “bring your own model” tutorials.

To choose, click on the left side “text to image.” You will find a variety of different models listed. Select one by hitting the “use” button. Then you will find yourself back on the interface where you can use the model by inserting your prompt.
UPDATE: We have just introduced the 'FLUX-schnell' model, the latest open-source innovation that has captivated the AI community. Typically, accessing such a model would involve navigating a complex technical process. However, we offer you the opportunity to explore it here for free.

Using the Prompt Helper

The prompt helper is automatically switched on, so while you type in the description of your image, it will give you text examples to choose from. They should increase the quality of the generated image. The “quality booster” influences the outcome significantly. It’s best to try it and see if it helps with what you wanted or if it changes the image too much.

Negative Prompts

The negative prompt is where you insert everything that you DON’T want to see, for example, “deformed hands,” “3 eyes,” or “blurry image.” Remember: There are use cases where these things don’t have to be excluded. A blurry image can be a core style choice for a perfect image. That is why we don’t switch these things on automatically.

Settings Overview

Sampler

First is the Sampler. You can experiment with it as it has a significant impact on the generation, but if you are unsure, just keep it on default.

Image Dimensions

Then there is Image Dimension. Decide here on the format, like square or vertical, for example.

Number of Images

The Number of Images indicates how many images will be generated at once. This provides you with a larger selection.

Time - Image Quality

Time - Image Quality refers to the number of steps required to generate an image. Think of it like creating a painting: the initial step provides a rough sketch, and with each additional step, the image becomes more detailed and precise. The quality of the image is therefore linked to the time invested in these steps. However, there is a point where further steps add no noticeable improvement. We've found that a range of 20 to 40 steps is typically sufficient, as increasing the steps beyond this range doesn't significantly enhance the image.

AI-Human Collaboration

Seed

The Seed can be thought of as the origin of your image, like the seed of a tree planted in the ground. If all conditions remain the same—same light, same amount of water, wind, temperature, etc.—the same tree will grow again. By hitting the lock image on the left, you can fix it. Otherwise, it will always randomize it.

ControlNet

If you want to learn more about ControlNet, switch to our ControlNet Tutorial to learn what this button is about.

Now you are all set and ready to hit the “create” button underneath the settings. A couple of seconds later, your image should appear.

We have tutorials on even more features in our blog-section. Have fun exploring our just go directly to Inpainting or background-removal