From the course: Hands-On Generative AI with Diffusion Models: Building Real-World Applications
Join today to access over 25,300 courses taught by industry experts.
Image-to-image translation with diffusion models
From the course: Hands-On Generative AI with Diffusion Models: Building Real-World Applications
Image-to-image translation with diffusion models
- [Instructor] Have you ever seen those playful illustrations where an artist jumps from a rudimentary stick figure to a masterpiece in just a few steps? Well, today we're going to do something similar, but with a technological twist. We'll be exploring the power of stable diffusion models to transform a text prompt and an input image into an astonishing final image. This process is simpler than drawing that horse, and you won't need a sketchbook. So let's dive right in. We start off with the text prompt and an input image. The text prompt directs the style or the theme of our output image, while the input image provides the basic blueprint. Our protagonist, the stable diffusion model, gradually morphs the input image guided by the text prompt to produce a final image. Converting the same process to code, most of our components remain the same except the stable diffusion image to image pipeline, which we will be importing from the Diffusers library. Going under the hood, the technical…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.