I think she’s popular among Stable Diffusion users because she looks decent, young, and consistent across a wide range of scenes. Her name is such a strong effect on the model. We want her outfit to be very detailed so she would look interesting.Įmma Watson as a powerful mysterious sorceress, casting lightning magic, detailed clothing Let’s say she is powerful and mysterious and uses lightning magic. I will defer this topic to a later part of this article.Īs a demo, let’s cast the sorceress to look like Emma Watson, the most used keyword in Stable Diffusion. However, be aware that these names may change not only the face but also the pose and something else. They have a strong effect and are an excellent way to control the subject’s appearance. We have to say exactly what we want.Ī common trick for human subjects is to use celebrity names. How do you want the sorceress to look? Any words describing her that would narrow down her image? What does she wear? What kind of magic is she casting? Is she standing, running, or floating in the air? What’s the background scene? That leaves too much room for imagination. Let’s say we want to generate a sorceress casting magic. A common mistake is not writing enough about the subjects. The subject is what you want to see in the image.
All images are generated with 30 steps of DPM++ 2M Karas sampler and an image size 512×704. Don’t worry, we will study negative prompts in the later part of this article. To see the effect of the prompt alone, I won’t be using negative prompts for now. Let’s review each category and generate some images by adding keywords from each. Treat them as a checklist to remind you what could be used.
You don’t have to include keywords from all categories. A good process is to look through a list of keyword categories and decide whether you want to use any of them.Īn extensive list of keywords from each category is available in the prompt generator. A good prompt needs to be detailed and specific.
0 kommentar(er)
