Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
| Date | Stars |
|---|---|
| 2026-07-31 | 1197 |
| 2026-08-06 | 1197 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<img src="docs/banner.png">
#### [[Project]](https://sites.google.com/view/stylegan-t/) [[PDF]](https://arxiv.org/abs/2301.09515) [[Video]](https://www.youtube.com/watch?v=MMj8OTOUIok)
This repository contains the **training code** for our paper "StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis". **We do not provide pretrained checkpoints.**
by [Axel Sauer](https://axelsauer.com/), [Tero Karras](https://research.nvidia.com/person/tero-karras), [Samuli Laine](https://research.nvidia.com/person/samuli-laine), [Andreas Geiger](https://www.cvlibs.net/), [Timo Aila](https://research.nvidia.com/person/timo-aila)
## Requirements ##
- Use the following commands with Miniconda3 to create and activate your environment:
```
conda create --name sgt python=3.9
conda activate sgt
conda install pytorch=1.9.1 torchvision==0.10.1 pytorch-cuda=11.6 -c pytorch -c nvidia
pip install -r requirements.txt
```
- GCC 7 or later compilers. The recommended GCC version depends on your CUDA version; see for example, CUDA 11.4 system requirements.
- If you run into problems when setting up the custom CUDA kernels, we refer to the [Troubleshooting docs](https://github.com/NVlabs/stylegan3/blob/main/docs/troubleshooting.md#why-is-cuda-toolkit-installation-necessary) of the StyleGAN3 repo.
## Data Preparation ##
StyleGAN-T can be trained on unconditional and conditional datasets. For small-scale experiments, we recommend zip datasets. When training on datasets with more than 1 million images, we recommend using webdatasets.
### Zip Dataset
Zip-Datasets are stored in the same format as in the previous iterations of [StyleGAN](https://github.com/NVlabs/stylegan3): uncompressed ZIP archives containing uncompressed PNG files and a metadata file `dataset.json` for labels. Custom datasets can be created from a folder containing images.
**CIFAR-10:** Download the [CIFAR-10 python version](https://www.cs.toronto.edu/~kriz/cifar.html) and convert to ZIP archive:
```.bash
python dataset_tool.py --source downloads/cifar10/cifar-10-python.tar.gz \
--dest data/cifar10-32x32.zip
```
**FFHQ:** Download the [Flickr-Faces-HQ dataset](https://github.com/NVlabs/ffhq-dataset) as 1024x1024 images and convert to ZIP archive at the same resolution:
```.bash
python dataset_tool.py --source downloads/ffhq/images1024x1024 \
--dest data/ffhq1024.zip --resolution 1024x1024
```
**COCO validation set:** The COCO validation set is used for tracking zero-shot FID and CLIP score. First, download the [COCO meta data](https://drive.google.com/file/d/1Xbg36mTJGG68RI_YgSPwhAE2msxgGfaC/view?usp=sharing). Then, run
```.bash
python dataset_tool.py --source downloads/captions_val2014.json \
--dest data/coco_val256.zip --resolution 256x256 --transform center-crop
```
It is recommend to prepare the dataset zip at the highest possible resolution, e.g. for FFHQ, the zip should contain images with 1024x1024 pixels. When training lower-resolution models, the training script can downsample the images on the fly.
### WebDataset
For preparing webdatasets, we used the excellent [img2dataset](https://github.com/rom1504/img2dataset) tool. Documentation for downloading different datasets can be found [here](https://github.com/rom1504/img2dataset/tree/main/dataset_examples). For our experiments, we used data from the following sources: [CC3M](https://ai.google.com/research/ConceptualCaptions/download), [CC12M](https://github.com/google-research-datasets/conceptual-12m), [YFFC100m](https://huggingface.co/datasets/dalle-mini/YFCC100M_OpenAI_subset), [Redcaps](https://huggingface.co/datasets/red_caps), [LAION-aesthetic-6plus](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6plus).
The joint dataset should have the following structure
```joint_dataset/
joint_dataset/cc3m/0000.tar
joint_dataset/cc3m/0001.tar
...
joint_dataset/laion_6plus/0000.tar
joint_dataset/laion_6plus/0001.tar
...
```
## Training ##
Training SExcerpt of 9,024 characters
Read on GitHub
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:36ff37b159c669b4, desc:text-to-image