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.
Diffusers and the Hugging Face ecosystem
From the course: Programming Generative AI: From Variational Autoencoders to Stable Diffusion with PyTorch and Hugging Face
Diffusers and the Hugging Face ecosystem
- Before we dive into the code using the Diffusers library from Hugging Face, I wanted to give a very quick overview of kind of the larger Hugging Face ecosystem in a similar way to when I presented PyTorch for the first time. Since there are a lot of interacting libraries, modules, components, and a lot of places you might need to or want to look to learn more about this library or any other library in the Hugging Face ecosystem. Now, Hugging Face itself is a company that has open source packages and a bunch of other aspects, like they have a hosted inference API, they have hosted data sets, and they also have commercial offerings. We'll only be looking at their open source things and libraries, and they actually have quite a few of them that happen to all inter-opt pretty nicely. So if we go to huggingface.co/docs, we can see the kind of main hub for all of the documentation here. We have the Transformers library, which we'll get into in the next lesson, which is really focused on…
Contents
-
-
-
-
-
-
(Locked)
Topics58s
-
(Locked)
Generation as a reversible process4m 55s
-
(Locked)
Sampling as iterative denoising4m 9s
-
(Locked)
Diffusers and the Hugging Face ecosystem6m 51s
-
(Locked)
Generating images with diffusers pipelines28m 20s
-
(Locked)
Deconstructing the diffusion process19m 9s
-
(Locked)
Forward process as encoder16m 47s
-
(Locked)
Reverse process as decoder7m 18s
-
(Locked)
Interpolating diffusion models9m 26s
-
(Locked)
Image-to-image translation with SDEdit8m 4s
-
(Locked)
Image restoration and enhancement11m 23s
-
(Locked)
-
-
-
-