Update README.md
Browse files
README.md
CHANGED
@@ -20,18 +20,18 @@ tags:
|
|
20 |
- **模型名稱**:hippojabe_style_image_generator
|
21 |
- **基礎模型**:基於 runwayml/stable-diffusion-v1-5
|
22 |
- **訓練圖像**:[小河馬實用貼圖--手繪風](https://store.line.me/stickershop/product/27243710/zh-Hant?from=sticker)
|
23 |
-
- **微調方法**:使用 DreamBooth 方法進行文本到圖像的微調
|
24 |
- **微調做法**:[只用24張圖複製我妹的畫風 - DreamBooth 微調 Stable Diffusion v1-5 實作教學](https://medium.com/@izzysde/只用24張圖複製我妹的畫風-dreambooth-微調stable-diffusion-v1-5-實作教學-3c3318362ebb)
|
25 |
|
26 |
|
27 |
-
#
|
28 |
|
29 |
-
## 安裝 diffusers, accelerate, cuda版torch
|
30 |
```bash
|
31 |
pip install diffusers, accelerate, torch==2.0.1+cu118 torchvision==0.15.2+cu118 torchaudio==2.0.2+cu118 -f https://download.pytorch.org/whl/cu118/torch_stable.html
|
32 |
```
|
33 |
|
34 |
-
## 生成圖片
|
35 |
```python
|
36 |
from diffusers import DiffusionPipeline
|
37 |
import torch
|
|
|
20 |
- **模型名稱**:hippojabe_style_image_generator
|
21 |
- **基礎模型**:基於 runwayml/stable-diffusion-v1-5
|
22 |
- **訓練圖像**:[小河馬實用貼圖--手繪風](https://store.line.me/stickershop/product/27243710/zh-Hant?from=sticker)
|
23 |
+
- **微調方法**:使用 [DreamBooth](https://huggingface.co/docs/diffusers/training/dreambooth) 方法進行文本到圖像的微調
|
24 |
- **微調做法**:[只用24張圖複製我妹的畫風 - DreamBooth 微調 Stable Diffusion v1-5 實作教學](https://medium.com/@izzysde/只用24張圖複製我妹的畫風-dreambooth-微調stable-diffusion-v1-5-實作教學-3c3318362ebb)
|
25 |
|
26 |
|
27 |
+
# 模型使用方法:
|
28 |
|
29 |
+
## 1. 安裝 diffusers, accelerate, cuda版torch
|
30 |
```bash
|
31 |
pip install diffusers, accelerate, torch==2.0.1+cu118 torchvision==0.15.2+cu118 torchaudio==2.0.2+cu118 -f https://download.pytorch.org/whl/cu118/torch_stable.html
|
32 |
```
|
33 |
|
34 |
+
## 2. 生成圖片
|
35 |
```python
|
36 |
from diffusers import DiffusionPipeline
|
37 |
import torch
|