Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
task_categories:
|
| 4 |
+
- text-to-video
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
tags:
|
| 8 |
+
- anime
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
This is https://huggingface.co/datasets/strangeman3107/animov-0.1 model by strangeman3107 that was converted by [me](https://github.com/kabachuha) into the ModelScope original format using this script https://github.com/ExponentialML/Text-To-Video-Finetuning/pull/52.
|
| 12 |
+
|
| 13 |
+
Ready to use in Auto1111 webui with this extension https://github.com/deforum-art/sd-webui-text2video
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
Now, copyting info from the original page
|
| 18 |
+
|
| 19 |
+
This is a text2video model for diffusers, fine-tuned with a [modelscope](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b) to have an anime-style appearance.
|
| 20 |
+
It was trained at 384x384 resolution.
|
| 21 |
+
It still generates unstable content often. The usage is the same as with the original modelscope model.
|
| 22 |
+
|
| 23 |
+
example images are [here](https://imgur.com/a/sCwmKG1).
|