lightweight-gan
awesome-generative-modeling
Our great sponsors
lightweight-gan | awesome-generative-modeling | |
---|---|---|
10 | 1 | |
1,599 | 159 | |
- | - | |
3.2 | 10.0 | |
over 1 year ago | about 3 years ago | |
Python | ||
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lightweight-gan
-
[D] My embarrassing trouble with inverting a GAN generator. Do GAN questions still get answered? ;-)
GAN details: I trained using the code from https://github.com/lucidrains/lightweight-gan, image size is 256, attn-res-layers is [32,64], disc_output_size is 5 and I trained with AMP.
-
I trained AI to generate OMORI image
Long short story, i trained AI called 'Lightweight' GAN with some image from the game (Steam version). The result isn't satisfying (either too similar with original image or distorted), but i decided to share it since it took 3-4 days.
-
Imagined ML model deployment on normal machine, is it possible?
Code for training your own [original] [simple] [light]
-
[P] - These Nebulae Do Not Exist
Trained lightweight-gan on public domain nebulae images. The blogpost covers how it was assembled end-to-end, from data scraping, to model training, and finally deploying it as a web app using free cloud services only
- Questi politici italiani non esistono
-
It begins! [Sixth World Music Comp Update]
https://github.com/lucidrains/stylegan2-pytorch is the simplest implementation I know of, and https://github.com/lucidrains/lightweight-gan is similar but designed for relatively lower performance machines.
- Bow Generation Using Lightweight GAN (In Progress)
-
GAN-generated Minecraft skins
I also regret using https://github.com/lucidrains/lightweight-gan over the standard StyleGAN2. The training time wasn't an issue for 128x128 images and I should have gone for the higher quality model.
- GAN-generated "Now That's What I Call Music!" CDs
-
GAN-generated "Now That's What I Call Music!" covers
It's hard to tell if the medicore results are due to the small dataset (~305 semi-aligned images, yes there's that many of these) or my own inexperience in GAN generation (i used https://github.com/lucidrains/lightweight-gan and the only changes i made from the defaults were to decrease the batch size and add color augmentation)
awesome-generative-modeling
-
[D] My embarrassing trouble with inverting a GAN generator. Do GAN questions still get answered? ;-)
Found relevant code at https://github.com/zhoubolei/awesome-generative-modeling + all code implementations here
What are some alternatives?
anycost-gan - [CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
vaegan - An implementation of VAEGAN (variational autoencoder + generative adversarial network).
HyperGAN - Composable GAN framework with api and user interface
stylegan2 - StyleGAN2 - Official TensorFlow Implementation
pi-GAN-pytorch - Implementation of π-GAN, for 3d-aware image synthesis, in Pytorch
ALAE - [CVPR2020] Adversarial Latent Autoencoders
gigagan-pytorch - Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
GlowIP - Code to reproduce results from "Invertible generative models for inverse problems: mitigating representation error and dataset bias"