Junho Kim

did you solve this problem ?

is it solved ?

To accurately reflect the style of the user image, a description of that image is necessary. Some users may struggle to write effective descriptions, we have not included this aspect...

* There is an issue about HF gpu, so HF is currently fixing it. * For this reason, the features for user image styles have been implemented, but not executed...

@dhmiller123 @SoftologyPro In local, you can try with `vsp_real_script.py`

We have recently updated the demo to reflect user images. However, due to an issue with the GPU provided by Hugging Face (HF), the functionality is not performing as expected....

demo is working now.

Yes. I think no problem.

Yes I'm going to release it soon. But I think I'll release only about the male2female.

I didn't train about smile dataset. I think the author will release it. [pytorch_author_code](https://github.com/WonwoongCho/GDWCT) I'm doing male2female to make sure my code works properly.