Commit
•
24ae4cd
1
Parent(s):
09bc880
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ introduction:(this is an nsfw motion lora model/Research on motion models using
|
|
| 25 |
4.training model:aamAnyloraAnimeMixAnime_v1.safetensors, inference model:mistoonAnime_v20.safetensors
|
| 26 |
5.additionally necessary specify parameters：use_offset_noise: true
|
| 27 |
6.learning_rate/learning_rate_spatial/adam_weight_decay:between 5x-20xoriginal learning_rate=depending on your training set counts
|
| 28 |
-
7.Suitable for Animatediff workflow <workflow in files> weight recommended in between 0.5-1
|
| 29 |
8.spatial_unet.safetensors<This is an optional model>Suggested weight in 0.2-0.3,
|
| 30 |
depends on the elements want you want for output, this is same as ordinary SD lora,So unnecessary or someone can have a try in some case
|
| 31 |
9.Add unet tab, 500steps model,1200steps model
|
|
|
|
| 25 |
4.training model:aamAnyloraAnimeMixAnime_v1.safetensors, inference model:mistoonAnime_v20.safetensors
|
| 26 |
5.additionally necessary specify parameters：use_offset_noise: true
|
| 27 |
6.learning_rate/learning_rate_spatial/adam_weight_decay:between 5x-20xoriginal learning_rate=depending on your training set counts
|
| 28 |
+
7.Suitable for Animatediff workflow <workflow(sexv2.json) in files> weight recommended in between 0.5-1
|
| 29 |
8.spatial_unet.safetensors<This is an optional model>Suggested weight in 0.2-0.3,
|
| 30 |
depends on the elements want you want for output, this is same as ordinary SD lora,So unnecessary or someone can have a try in some case
|
| 31 |
9.Add unet tab, 500steps model,1200steps model
|