lucidrains/gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
PythonMIT
Issues
- 1
support 256x256 images
#55 opened by YoucanBaby - 2
Video?
#59 opened by darkzbaron - 0
- 1
Loss turned `NaN` when custom training
#56 opened by yasohasakii - 1
Multi GPU with gradient accumulation
#37 opened by dprze - 1
Standard Attention vs ViTGAN Attention
#54 opened by jfischoff - 4
[News] Videogigagan is published.
#53 opened by O-O1024 - 2
Has Anyone Trained This Model Yet?
#48 opened by PaulFidika - 122
Training plans?
#17 opened by nbardy - 16
- 2
the loss became nan after a few train steps
#52 opened by boya34 - 1
question about code in unet_upsampler.py
#51 opened by 8639sung - 0
Config to reproduce paper
#50 opened by dawgster - 0
The text-to-image tasks
#49 opened by SYZhang0805 - 0
How to use this model for SR ?
#47 opened by LilyTheBear - 10
Gradient Penalty is very high in the start
#46 opened by inspirit - 7
to_rgb branch has only 1 learnable kernel
#45 opened by inspirit - 1
Wrong order of resolutions list
#44 opened by inspirit - 2
- 2
How to implement this model to enhance my input images? Do I have to train the model to use?
#41 opened by Mr-Nobody-dey - 1
Weights of Gigagan Upscaler
#42 opened by dheerajpant700 - 2
[Question] About the upscaler
#35 opened by LouSparfell - 0
Confused about this project?
#39 opened by Maki9009 - 0
- 4
Multi GPU training
#36 opened by dprze - 3
Possible Discrepancies
#33 opened by randintgenr - 2
- 10
What makes the gan upsampler so effective
#7 opened by salvadog - 3
- 5
- 4
Hardware Requirements
#32 opened by kaykyr - 1
Why change the collection of rgb in upsampler?
#30 opened by XavierXiao - 2
How do I run inference with this model?
#13 opened by kct22aws - 2
Some minor questions regarding the design
#29 opened by XavierXiao - 10
Questions regarding the discriminator
#19 opened by XavierXiao - 1
fidelity
#15 opened by Inferencer - 2
Generator/Discriminator dim Argument
#26 opened by CerebralSeed - 8
- 10
L2 attention is implemented wrong!
#14 opened by PeterL1n - 8
Question about discriminator
#12 opened by Zijian007 - 7
- 2
If I can just use the super resolution module to do some SR task? How long can you finish the sr moddules
#11 opened by Shawn-Yu-1 - 5
License Violation Issue
#8 opened by CerebralSeed - 2
basic setup/install documentation
#5 opened by djo267 - 1
Is this project ready to train?
#6 opened by kaykyr - 5
How can I use this?
#4 opened by AceBeaker2 - 1
How far is this codebase?
#3 opened by stencilman - 1
Implement dynamic convulsion
#2 opened by Jainam2130 - 4
Pretrained models
#1 opened by IceClear