[HN Gopher] Show HN: Modular Diffusion - A modular Python librar...
___________________________________________________________________
Show HN: Modular Diffusion - A modular Python library for diffusion
models
Hello everyone! I've been working on this project for a few months
as part of my thesis in Machine Learning. It's meant to be a
library that provides an easy-to-use but flexible API to design and
train Diffusion Models. I decided to make it because I wanted to
quickly prototype a Diffusion Model but there were no good tools to
do it with. I think it really can help people prototype their own
Diffusion Models a lot faster and only in a few lines of code. The
base idea is to have a Model class that takes different modules
corresponding to the different aspects of the Diffusion Model
process (noise schedule, noise type, denoising network, loss
function, guidance, etc.) and allow the user to mix and match
different modules to achieve different results. The library ships
with a bunch of prebuilt modules and the plan is to add many more.
I also made it super easy to implement your own modules, you just
need to extend from one of the base classes available. Contrary to
HuggingFace Diffusers, this library is focused on designing and
training your own Diffusion Models rather than finetuning
pretrained ones (although this is possible). I would really
appreciate your feedback.
Author : secularchapel
Score : 26 points
Date : 2023-09-02 14:16 UTC (8 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| bgoldste wrote:
| Nifty! Look forward to checking this out. What kind of hardware
| do you roughly need to run this, though I'm guessing there's a
| range depending on what you're doing?
___________________________________________________________________
(page generated 2023-09-02 23:01 UTC)