Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## Potat 1️⃣
|
2 |
+
First Open-Source 1024x576 Text To Video Model 🥳
|
3 |
+
|
4 |
+
### Info
|
5 |
+
Prototype Model <br />
|
6 |
+
Trained with https://lambdalabs.com ❤ 1xA100 (40GB) <br />
|
7 |
+
2197 clips, 68388 tagged frames ( [salesforce/blip2-opt-6.7b-coco](https://huggingface.co/Salesforce/blip2-opt-6.7b-coco) ) <br />
|
8 |
+
train_steps: 10000 <br />
|
9 |
+
|
10 |
+
|
11 |
+
### Dataset & Config
|
12 |
+
https://huggingface.co/camenduru/potat1_dataset/tree/main
|
13 |
+
|
14 |
+
### Repos
|
15 |
+
https://github.com/Breakthrough/PySceneDetect <br />
|
16 |
+
https://github.com/ExponentialML/Video-BLIP2-Preprocessor <br />
|
17 |
+
https://github.com/ExponentialML/Text-To-Video-Finetuning <br />
|
18 |
+
https://github.com/camenduru/Text-To-Video-Finetuning-colab <br />
|
19 |
+
|
20 |
+
### Base Model
|
21 |
+
https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis <br />
|
22 |
+
https://www.modelscope.cn/models/damo/text-to-video-synthesis <br />
|
23 |
+
|
24 |
+
Thanks to ModelScope ❤ ExponentialML ❤ @DiffusersLib ❤ @LambdaAPI ❤ @cerspense ❤ @CiaraRowles1 ❤ @p1atdev_art ❤ <br />
|
25 |
+
|
26 |
+
Please try it 🐣 <br />
|
27 |
+
|
28 |
+
Potat 2️⃣ is in the oven ♨ <br />
|