Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,13 @@ introduction:(this is a motion lora model/Research on motion models about Beam a
|
|
| 12 |
2.any commercial legal disputes arising from the use of this model shall be borne by yourself.
|
| 13 |
3.if you install this model that implies that you accept the terms.
|
| 14 |
---
|
| 15 |
-
*example 2K result has been released on the youtube(https://www.youtube.com/watch?v=s_NdPdkbNqU)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
2.any commercial legal disputes arising from the use of this model shall be borne by yourself.
|
| 13 |
3.if you install this model that implies that you accept the terms.
|
| 14 |
---
|
| 15 |
+
*example 2K result has been released on the youtube(https://www.youtube.com/watch?v=s_NdPdkbNqU)
|
| 16 |
+
|
| 17 |
+
**motion lora model configuration
|
| 18 |
+
1.train in 1024x576size 256rank 16framesx5 1500steps
|
| 19 |
+
2.six videos input with folder training with 3 types of text config
|
| 20 |
+
3.trian prompt:"a highly quality clear best realistic video of high speed shuttle with light"
|
| 21 |
+
4.training model:epicrealism_naturalSinRC1VAE.safetensors, inference model:epicrealism_naturalSinRC1VAE.safetensors
|
| 22 |
+
5.additionally necessary specify parameters：use_offset_noise: true
|
| 23 |
+
6.learning_rate/learning_rate_spatial/adam_weight_decay:between 5x-20xoriginal learning_rate=depending on your training set counts
|
| 24 |
+
7.Suitable for Animatediff workflow, weight recommended in between 0.5-1
|