Sho commited on
Commit
4da4d66
1 Parent(s): 27cab1e

DOC: minor update

Browse files
Files changed (1) hide show
  1. README.md +40 -40
README.md CHANGED
@@ -1,41 +1,41 @@
1
- ---
2
- license: mit
3
- library_name: pytorch
4
- tags:
5
- - image-generation
6
- - gan
7
- - stylegan
8
- - stylegan3
9
- - nvidia
10
- ---
11
-
12
- # Anime Faces Generator (StyleGAN3 by NVIDIA)
13
-
14
- <img width="679" alt="Generated Faces" src="https://user-images.githubusercontent.com/35907066/161809457-e6467724-5942-4a89-b379-85ddfd6ac86c.png">
15
-
16
- This is a [StyleGAN3 PyTorch](https://github.com/NVlabs/stylegan3) model trained on this [Anime Face Dataset](https://github.com/bchao1/Anime-Face-Dataset).
17
-
18
- ### Usage
19
-
20
- Demo on Spaces is not yet implemented.
21
-
22
- You can run the model pickle file locally using the instructions in this generator-script-only subset of the StyleGAN3 repo:
23
- - https://github.com/venture-anime/stylegan3-anime-faces-generator
24
-
25
- ### Dataset & Model Details
26
-
27
- The [Anime Face Dataset](https://github.com/bchao1/Anime-Face-Dataset) was created by Mckinsey666.
28
-
29
- Training was done in [Paperspace Gradient](https://gradient.run/) on a free `RTX-5000` instance with the following parameters:
30
-
31
- - Configuration: `stylegan3-t`
32
- - GPUs: `1`
33
- - Batch Size: `8`
34
- - Gamma: `0.5`
35
- - Final tick: `102`
36
- - Final FID50k value (this pickle): `9.26043547642206`.
37
-
38
- # Train your own StyleGAN3 on PaperSpace or Colab
39
-
40
- You can use the notebooks here for a ready-to-use training pipeline
41
  https://github.com/akiyamasho/stylegan3-training-notebook
 
1
+ ---
2
+ license: mit
3
+ library_name: pytorch
4
+ tags:
5
+ - image-generation
6
+ - gan
7
+ - stylegan
8
+ - stylegan3
9
+ - nvidia
10
+ ---
11
+
12
+ # Anime Faces Generator (StyleGAN3 by NVIDIA)
13
+
14
+ <img width="679" alt="Generated Faces" src="https://user-images.githubusercontent.com/35907066/161809457-e6467724-5942-4a89-b379-85ddfd6ac86c.png">
15
+
16
+ This is a [StyleGAN3 PyTorch](https://github.com/NVlabs/stylegan3) model trained on this [Anime Face Dataset](https://github.com/bchao1/Anime-Face-Dataset).
17
+
18
+ ### Usage
19
+
20
+ Demo on Spaces is not yet implemented.
21
+
22
+ You can run the model pickle file locally using the instructions in this generator-script-only subset of the StyleGAN3 repo:
23
+ - https://github.com/venture-anime/stylegan3-anime-faces-generator
24
+
25
+ ### Dataset & Model Details
26
+
27
+ The [Anime Face Dataset](https://github.com/bchao1/Anime-Face-Dataset) was created by Mckinsey666.
28
+
29
+ Training was done in [Paperspace Gradient](https://gradient.run/) on a free `RTX-5000` instance with the following parameters:
30
+
31
+ - Configuration: `stylegan3-t`
32
+ - GPUs: `1`
33
+ - Batch Size: `8`
34
+ - Gamma: `0.5`
35
+ - Final tick: `102`
36
+ - Final fid50k_full value (this pickle): `9.26043547642206`.
37
+
38
+ # Train your own StyleGAN3 on PaperSpace or Colab
39
+
40
+ You can use the notebooks here for a ready-to-use training pipeline
41
  https://github.com/akiyamasho/stylegan3-training-notebook