Update README.md
Browse files
README.md
CHANGED
|
@@ -78,8 +78,15 @@ For training flash version we used the following architecture of discriminator.
|
|
| 78 |
|
| 79 |
<img src="https://github.com/ai-forever/Kandinsky-4/blob/main/assets/discriminator.png"> <img src="https://github.com/ai-forever/Kandinsky-4/blob/main/assets/discriminator_head.png">
|
| 80 |
|
|
|
|
| 81 |
|
| 82 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
```python
|
| 84 |
import torch
|
| 85 |
from IPython.display import Video
|
|
|
|
| 78 |
|
| 79 |
<img src="https://github.com/ai-forever/Kandinsky-4/blob/main/assets/discriminator.png"> <img src="https://github.com/ai-forever/Kandinsky-4/blob/main/assets/discriminator_head.png">
|
| 80 |
|
| 81 |
+
## Installation
|
| 82 |
|
| 83 |
+
```bash
|
| 84 |
+
git clone https://github.com/ai-forever/Kandinsky-4.git
|
| 85 |
+
cd Kandinsky-4
|
| 86 |
+
pip install -r kandinsky4_video2audio/requirements.txt
|
| 87 |
+
```
|
| 88 |
+
|
| 89 |
+
## Inference:
|
| 90 |
```python
|
| 91 |
import torch
|
| 92 |
from IPython.display import Video
|