ProGamerGov commited on
Commit
8f55b78
1 Parent(s): e9524cd

Better training description

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -10,15 +10,15 @@ The embeddings in this repository were trained for the 768px [Stable Diffusion v
10
 
11
  **Knollingcase v1**
12
 
13
- The v1 embeddings were trained for 4000 iterations with a batch size of 2, a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 69 training images were used.
14
 
15
  **Knollingcase v2**
16
 
17
- The v2 embeddings were trained for 5000 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 78 training images were used.
18
 
19
  **Knollingcase v3**
20
 
21
- The v3 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 86 training images were used.
22
 
23
  <div align="center">
24
  <img src="https://huggingface.co/ProGamerGov/knollingcase-embeddings-sd-v2-0/resolve/main/cruise_ship_on_wave_kc16-v3-6250.png">
@@ -29,7 +29,7 @@ The v3 embeddings were trained for 4000-6250 iterations with a batch size of 4 a
29
 
30
  **Knollingcase v4**
31
 
32
- The v4 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, using Automatic1111's WebUI. A total of 116 training images were used.
33
 
34
 
35
  To use the embeddings, download and then rename the file to whatever trigger word you want to use.
 
10
 
11
  **Knollingcase v1**
12
 
13
+ The v1 embeddings were trained for 4000 iterations with a batch size of 2, a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 69 training images with high quality captions were used.
14
 
15
  **Knollingcase v2**
16
 
17
+ The v2 embeddings were trained for 5000 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 78 training images with high quality captions were used.
18
 
19
  **Knollingcase v3**
20
 
21
+ The v3 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 86 training images with high quality captions were used.
22
 
23
  <div align="center">
24
  <img src="https://huggingface.co/ProGamerGov/knollingcase-embeddings-sd-v2-0/resolve/main/cruise_ship_on_wave_kc16-v3-6250.png">
 
29
 
30
  **Knollingcase v4**
31
 
32
+ The v4 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, using Automatic1111's WebUI. A total of 116 training images with high quality captions were used.
33
 
34
 
35
  To use the embeddings, download and then rename the file to whatever trigger word you want to use.