Update README.md
Browse files
README.md
CHANGED
@@ -152,19 +152,17 @@ tags:
|
|
152 |
|
153 |
## Introduction
|
154 |
BunnyMint is a Pony model based on two finetunes. The first finetune was trained on 8k randomly selected artist images with score:>99 from danbooru for 10 epochs to improve overall aesthetic. The second finetune was trained again on 20k hand picked NAIv3 images for 20 epochs. Personally trained Blue Archive LoRA was then merged on top to make style more alligned with personal preferences.
|
155 |
-
```
|
156 |
-
Total Steps:
|
157 |
-
- 8k artist image/10 Epochs
|
158 |
-
- 20k NAIv3 dataset/20 Epochs
|
159 |
-
Total steps: ~480k steps
|
160 |
-
```
|
161 |
-
|
162 |
|
163 |
## Donate
|
164 |
**Finetuning models on personal hardware is pretty costly, so if anyone likes what I do and feels like it, here's my gumroad:**
|
165 |
|
166 |
**https://lylogummy.gumroad.com/l/avhut**
|
167 |
|
|
|
|
|
|
|
|
|
|
|
168 |
## Usage
|
169 |
|
170 |
### Sample prompt
|
|
|
152 |
|
153 |
## Introduction
|
154 |
BunnyMint is a Pony model based on two finetunes. The first finetune was trained on 8k randomly selected artist images with score:>99 from danbooru for 10 epochs to improve overall aesthetic. The second finetune was trained again on 20k hand picked NAIv3 images for 20 epochs. Personally trained Blue Archive LoRA was then merged on top to make style more alligned with personal preferences.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
|
156 |
## Donate
|
157 |
**Finetuning models on personal hardware is pretty costly, so if anyone likes what I do and feels like it, here's my gumroad:**
|
158 |
|
159 |
**https://lylogummy.gumroad.com/l/avhut**
|
160 |
|
161 |
+
## Training
|
162 |
+
**- 8k artist image/10 Epochs**
|
163 |
+
**- 20k NAIv3 dataset/20 Epochs**
|
164 |
+
**Total steps: ~480k steps**
|
165 |
+
|
166 |
## Usage
|
167 |
|
168 |
### Sample prompt
|