Update readme
Browse files
README.md
CHANGED
|
@@ -16,6 +16,12 @@ AnimateDiff-Lightning is a lightning-fast text-to-video generation model. It can
|
|
| 16 |
|
| 17 |
Our models are distilled from [AnimateDiff SD1.5 v2](https://huggingface.co/guoyww/animatediff). This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is great. Our 1-step model is only provided for research purposes.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Recommendation
|
| 20 |
|
| 21 |
AnimateDiff-Lightning produces the best results when used with stylized base models. We recommend using the following base models:
|
|
|
|
| 16 |
|
| 17 |
Our models are distilled from [AnimateDiff SD1.5 v2](https://huggingface.co/guoyww/animatediff). This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is great. Our 1-step model is only provided for research purposes.
|
| 18 |
|
| 19 |
+
|
| 20 |
+
## Demo
|
| 21 |
+
|
| 22 |
+
Try AnimateDiff-Lightning using our text-to-video generation [demo](https://huggingface.co/spaces/ByteDance/AnimateDiff-Lightning).
|
| 23 |
+
|
| 24 |
+
|
| 25 |
## Recommendation
|
| 26 |
|
| 27 |
AnimateDiff-Lightning produces the best results when used with stylized base models. We recommend using the following base models:
|