Now modify the prompt to include blending of two faces. In the inpainting canvas, draw a mask covering the face. Inpainting is a technique to keep both the composition and have total control of the face.Īfter generating an image in txt2img tab, click on Send to inpainting. Using this technique, we can keep the composition while controlling the face to some extent.
#Fashion model dress drawing skin#
Photo of young, highlight hair, sitting outside restaurant, wearing dress, rim lighting, studio lighting, looking at the camera, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8K UHD, highly detailed glossy eyes, high detailed skin, skin pores This keeps the composition while offering to blend a generic face with a celebrity. Taking advantage of this idea, we can still use woman in the first few steps and only swap in a celebrity name later on. The overall composition is set by the first keyword because the sampler denoises most in the first few steps. Photos of actresses often associate with certain settings, such as award ceremonies. Blending one nameĭid you notice the background and composition have changed drastically when using two names? It’s the association effect. Photo of young woman,, highlight hair, sitting outside restaurant, wearing dress, rim lighting, studio lighting, looking at the camera, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8K UHD, highly detailed glossy eyes, high detailed skin, skin poresĭisfigured, ugly, bad, immature, cartoon, anime, 3d, painting, b&w īy carefully adjusting the factor, you can dial in the proportion of the two faces. You can simply throw that into the prompt like below. For example, with 20 steps means the prompt uses Ana de Armas in steps 1 – 10, and uses Emma Watson in steps 11-20.
It indicates the fraction of the total number of steps when the keyword switches from person 1 to person 2. The syntax in AUTOMATIC1111 isįactor is a number between 0 and 1. The trick is to blend two faces using prompt scheduling. So they are guaranteed to be consistent.īut we usually don’t want to use their face. Their looks are the most recognizable part of their bodies. Controlling faces Blending two namesĭo you want to generate the same look across multiple images? One trick is to take advantage of celebrities. Photo of young woman, highlight hair, sitting outside restaurant, wearing dress, rim lighting, studio lighting, looking at the camera, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8K UHD, highly detailed glossy eyes, high detailed skin, skin poresĪre you surprised that the base model can generate these high-quality realistic images? We haven’t even used special photo-realistic models yet. Putting them together, we have the following final prompt. These keywords intend to render a more realistic face.Ī side effect of using these keywords is drawing the subject closer to the camera. I cannot say they are definitely better, but it certainly doesn’t hurt to include them… Facial detailsįinally, some keywords can be used as sweeteners to describe eyes and skin. Photo of young woman, highlight hair, sitting outside restaurant, wearing dress, rim lighting, studio lighting, looking at the camera, dslr, ultra quality, sharp focus, tack sharp, dof, film grain, Fujifilm XT3, crystal clear, 8K UHD Keywords like dslr, ultra quality, 8K, UHD can improve the quality of images. I will tell you in the later part of the article. You may notice the anatomy is not quite right. The photos instantly look more interesting. Photo of young woman, highlight hair, sitting outside restaurant, wearing dress, rim lighting, studio lighting, looking at the camera Let’s add some lighting keywords and a keyword that controls the viewing angle. Lighting keywordsĪ large part of a photographer’s job is to set up good lighting.
There’s still a lot of room for improvement. The Upper bodies look pretty good.īut the anatomy of the lower bodies is still problematic.
It’s doing something: The women look better. It is intended to generate better anatomy and steer away from non-realistic styles.ĭisfigured, ugly, bad, immature, cartoon, anime, 3d, painting, b&w This negative prompt is quite minimalistic. Well, that didn’t go so well… Negative prompt Photo of young woman, highlight hair, sitting outside restaurant, wearing dress Let’s start with a simple prompt of a woman sitting outside of a restaurant.
#Fashion model dress drawing how to#
In this section, you will learn how to build a high-quality prompt for realistic photo styles step-by-step. You can use this GUI on Windows, Mac, or Google Colab. We will use AUTOMATIC1111 Stable Diffusion GUI to generate realistic people.
0 kommentar(er)
