Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- TempoFunk/webvid-10M
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- ali-vilab/text-to-video-ms-1.7b
|
| 9 |
+
tags:
|
| 10 |
+
- text-to-video
|
| 11 |
+
---
|
| 12 |
+
# caT text to video
|
| 13 |
+
|
| 14 |
+
Conditionally augmented text-to-video model. Uses pre-trained weights from modelscope text-to-video model, augmented with temporal conditioning transformers to extend generated clips and create a smooth transition between them.
|
| 15 |
+
|
| 16 |
+
This project was trained at home as a hobby.
|
| 17 |
+
|
| 18 |
+
## Installation
|
| 19 |
+
|
| 20 |
+
### Clone the Repository
|
| 21 |
+
|
| 22 |
+
```bash
|
| 23 |
+
git clone https://github.com/motexture/caT-text-to-video.git
|
| 24 |
+
cd caT
|
| 25 |
+
python -m venv venv
|
| 26 |
+
source venv/bin/activate # On Windows use `venv\Scripts\activate`
|
| 27 |
+
pip install -r requirements.txt
|
| 28 |
+
python run.py
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
Visit the provided URL in your browser to interact with the interface and start generating videos.
|