Comments (4)
Thank you guys! Thank you for sharing a bit of knowledge with me. I'll study imagen-pytorch.
from gigagan-pytorch.
@kaykyr thanks for the small sponsorship!
from gigagan-pytorch.
Just a quick note, no model are officially relaesed from this repo(and so have been trained fully and released), so you have to train from scratch, the computing requirements scales depending on the number of parameters you are creating for your model, a rtx 4090 is more than enough if you make a small model with small images, but if you choose bigger paramters in the gan architecture dimension(which means your gan will hold a bigger number of parameters), the memory requirements will scale accordingly, the best would be to start with a small model, take the example code provided, and experiment with the parameters, most of all the GigaGan parameters of the class in the code example will scale memory requirements up.
This repo is pretty new, you may want to use imagen-pytorch.
from gigagan-pytorch.
yea agreed with Axel. a lot of research papers have already came out using imagen-pytorch, while gigagan is still fairly new and no reported success training it yet
from gigagan-pytorch.
Related Issues (20)
- The training code not deal with paired data yet? HOT 2
- [Question] About the upscaler HOT 2
- Multi GPU training HOT 4
- Multi GPU with gradient accumulation
- [Request] Please provide a replicate.com version
- Confused about this project?
- NaN losses after hours of training (UPSAMPLER) HOT 16
- How to implement this model to enhance my input images? Do I have to train the model to use? HOT 2
- Weights of Gigagan Upscaler HOT 1
- Turn on/off gradients computation between generator/discriminator HOT 2
- Wrong order of resolutions list HOT 1
- to_rgb branch has only 1 learnable kernel HOT 7
- Gradient Penalty is very high in the start HOT 10
- How to use this model for SR ?
- Has Anyone Trained This Model Yet? HOT 2
- The text-to-image tasks
- Config to reproduce paper
- question about code in unet_upsampler.py HOT 1
- the loss became nan after a few train steps HOT 2
- [News] Videogigagan is published. HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gigagan-pytorch.