search

IIGROUP / TediGAN

[CVPR 2021] Pytorch implementation for TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
https://arxiv.org/abs/2012.03308
MIT License
373 stars 59 forks source link

Pretrained StyleGAN generator links #21

Open johnberg1 opened 3 years ago

johnberg1 commented 3 years ago

Hello, thank you for your contribution.

The links you have provided for the pretrained StyleGAN generator for cub_bird_256 and lsun_bird_256 seem to be broken, giving a "page not found" error. Could you please update those links?

weihaox commented 2 years ago

We planned to extend our method from face to bird images to facilitate direct comparison of other text-to-image generation method, which are mostly trained on Bird and COCO. We only finished part of it before putting it aside. I trained a model with part of the lsun bird dataset, but I’m not sure if the pretrained model could be found. The framework is the same, first training StyleGAN and then train the encoder, just change the dataset from images of faces to birds.