daebakgazua commited on
Commit
cb45af9
·
verified ·
1 Parent(s): 4a83c1f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -3
README.md CHANGED
@@ -1,3 +1,32 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model:
4
+ - StyleGAN
5
+ ---
6
+
7
+ ## 1. Overview
8
+
9
+ **StyleGAN-VectorFind-v6,v7** models for [Oh-LoRA v2 Project](https://github.com/WannaBeSuperteur/AI_Projects/tree/main/2025_05_02_OhLoRA_v2).
10
+
11
+ * These models are Fine-Tuned version of [GenForce StyleGAN celeba_partial-256x256](https://github.com/genforce/genforce/blob/master/MODEL_ZOO.md).
12
+ * Finally decided to use **StyleGAN-VectorFind-v7 (```stylegan_gen_vector_find_v7.pth```)**.
13
+ * Detailed info
14
+ * [StyleGAN-VectorFind-v6 Detailed info (in Korean)](https://github.com/WannaBeSuperteur/AI_Projects/tree/main/2025_05_02_OhLoRA_v2/stylegan#3-2-stylegan-finetune-v1-%EA%B8%B0%EB%B0%98-%ED%95%B5%EC%8B%AC-%EC%86%8D%EC%84%B1%EA%B0%92-%EB%B3%80%ED%99%98-latent-z-vector-%ED%83%90%EC%83%89-stylegan-vectorfind-v6)
15
+ * [StyleGAN-VectorFind-v7 Detailed info (in Korean)](https://github.com/WannaBeSuperteur/AI_Projects/tree/main/2025_05_02_OhLoRA_v2/stylegan#3-3-stylegan-finetune-v1-%EA%B8%B0%EB%B0%98-%ED%95%B5%EC%8B%AC-%EC%86%8D%EC%84%B1%EA%B0%92-%EB%B3%80%ED%99%98-intermediate-w-vector-%ED%83%90%EC%83%89-stylegan-vectorfind-v7)
16
+
17
+ ## 2. Model files & save path for usage
18
+
19
+ All models have the same save path for usage : ```2025_05_02_OhLoRA_v2/stylegan/models/{model_file_name}```.
20
+
21
+ * Generator
22
+
23
+ |Version|Model|Finally decided to use|
24
+ |---|---|---|
25
+ |StyleGAN-VectorFind-v6|```stylegan_gen_vector_find_v6.pth```||
26
+ |StyleGAN-VectorFind-v7|```stylegan_gen_vector_find_v7.pth```|✅|
27
+
28
+ * Conv-NN for property score computation
29
+
30
+ |Version|Model type|Model|Finally decided to use|
31
+ |---|---|---|---|
32
+ |StyleGAN-FineTune-v2|CNN (for property score computation)|```stylegan_gen_fine_tuned_v2_cnn.pth```|✅|