From the course: Programming Generative AI: From Variational Autoencoders to Stable Diffusion with PyTorch and Hugging Face

Unlock this course with a free trial

Join today to access over 24,800 courses taught by industry experts.

Generative text effects with font depth maps

Generative text effects with font depth maps

From the course: Programming Generative AI: From Variational Autoencoders to Stable Diffusion with PyTorch and Hugging Face

Start my 1-month free trial Buy for my team

Generative text effects with font depth maps

“

- [Instructor] And to finish up, the last thing I just want to show is more of a fun example. And you may have seen similar things. There's an Adobe tool that lets you, basically, generate images in the shape of text. There's some Google tools out there that basically do the same thing. For this, I want to show that you don't necessarily need to derive a depth map from an existing image. So this is a way to, basically, handcraft what to the model is a depth map. But I generated this image in just Adobe Illustrator with text, Jonathan, and kind of this bubbly font. There's some shadows on it. It's a little three-dimensional. And we can actually use this image since it's basically just black and white. It's of the same encoding and structure of the depth maps we are feeding into the ControlNet. So if you do want to generate your own depth maps, basically just code something up, maybe make some generative depth map with white and black corresponding to near and far. You can feed anything…

Contents