TencentARC/GFPGAN
1
0
Fork 0
mirror of https://github.com/TencentARC/GFPGAN.git synced 2026-04-25 15:20:58 +00:00
Code Issues 476 Packages Projects Releases 8 Wiki Activity

How to train the StyleGAN2Generator used as prior knowledge if i want to make some modifications #326

New Issue
Open
opened 2026-01-29 21:46:51 +00:00 by claunia · 3 comments
claunia commented 2026-01-29 21:46:51 +00:00
Owner
Copy Link

Originally created by @NJUPT-IPR-ZhuWeihong on GitHub (Mar 22, 2023).

Ur work is amazing! I want to make some modifications in the StyleGAN2Generator network.Due to modifications above,the pretrained models of StyleGAN2Generator cannot be used any more.What's more,as ur paper mentioned, generative facial prior gives rise to performance improvement.
Therefore, I have to train StyleGAN2Generator solely to achieve better performance.I am wondering if i could just modify the official Pytorch StyleGAN2 code(the train file, mainly the network architecture) and the model file will adapt to GFPGAN. Of course i modify GFPGAN(the train file and the inference file) at the same time.
Is there any tips or warnings?
It will be appreciated a lot if i could get ur guidance.
Whatever, thanks for ur amazing work in FSR again!

Originally created by @NJUPT-IPR-ZhuWeihong on GitHub (Mar 22, 2023). Ur work is amazing! I want to make some modifications in the StyleGAN2Generator network.Due to modifications above,the pretrained models of StyleGAN2Generator cannot be used any more.What's more,as ur paper mentioned, generative facial prior gives rise to performance improvement. Therefore, I have to train StyleGAN2Generator solely to achieve better performance.I am wondering if i could just modify the official Pytorch StyleGAN2 code(the train file, mainly the network architecture) and the model file will adapt to GFPGAN. Of course i modify GFPGAN(the train file and the inference file) at the same time. Is there any tips or warnings? It will be appreciated a lot if i could get ur guidance. Whatever, thanks for ur amazing work in FSR again!
claunia commented 2026-01-29 21:46:51 +00:00
Author
Owner
Copy Link

@NJUPT-IPR-ZhuWeihong commented on GitHub (Mar 22, 2023):

I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work?
I don't know.Trying...

@NJUPT-IPR-ZhuWeihong commented on GitHub (Mar 22, 2023): I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work? I don't know.Trying...
claunia commented 2026-01-29 21:46:52 +00:00
Author
Owner
Copy Link

@zzuyb commented on GitHub (May 17, 2023):

I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work? I don't know.Trying...

Can it be used normally？

@zzuyb commented on GitHub (May 17, 2023): > I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work? I don't know.Trying... Can it be used normally？
claunia commented 2026-01-29 21:46:52 +00:00
Author
Owner
Copy Link

@NJUPT-IPR-ZhuWeihong commented on GitHub (May 18, 2023):

I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work? I don't know.Trying...

Can it be used normally？

yes,just modify some parameters according to ur requirements

@NJUPT-IPR-ZhuWeihong commented on GitHub (May 18, 2023): > > I found a yml file in basicsr\options\train\StyleGAN, named train_StyleGAN2_256_Cmul2_FFHQ.yml.Maybe it will work? I don't know.Trying... > > Can it be used normally？ yes,just modify some parameters according to ur requirements
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
pull-request
Mirrored from GitHub Pull Request
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
claunia
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#326
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?