Cseti commited on
Commit
f8be430
1 Parent(s): 8a76c3d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -0
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Basic camera motion LoRAs for Animatediff v2 motion models - version 1
2
+
3
+ ## Model Description
4
+ This repository contains a collection of basic camera motion LoRAs finetuned on Animatediff v2 models. The training process utilized Kijai's [AnimateDiff Motion Director ComfyUI nodes](https://github.com/kijai/ComfyUI-ADMotionDirector). These LoRAs have been tested exclusively in ComfyUI with Kosinkadink's [AnimateDiff-Evolved nodes](https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved), however they may be compatible with other AnimateDiff implementations.
5
+
6
+ ## File summary
7
+
8
+ | Name | Compatible Motion Model | Base AR (w/h) | Frames | input videos |
9
+ | ------------------------------------------------------------- | ----------------------- | ------------- | ------ | ------------ |
10
+ | <name>.safetensors | v2 | (1:1) | 32 | 70 |
11
+
12
+ ## How to use
13
+ - copy the motion lora files into your "ComfyUI\models\animatediff_motion_lora" folder
14
+ - Use the "Load Animatediff LoRA" node
15
+ - set the context_length parameter to 32 and context_overlap to 8 (it might work with other values but this is how I tested it)
16
+
17
+ ## Settings and recommendations
18
+ - Use it with strength: 0.8
19
+ - This motion LoRA is finetuned on a v2 motion model. It works also with AnimateLCM but don't work with v3 models
20
+ - It works with SD 1.5 checkpoints
21
+ - Animatediff v3 adapter LoRA is recommended regardless it is a v2 model.
22
+ - If you want more motion try increasing the scale multival or lower the strength of the v3 adapter LoRA
23
+ - Try playing with the strength of
24
+ - motion LoRA
25
+ - scale multival
26
+ - v3_adapter lora
27
+
28
+ like increasing the scale multival and lowering the lora strength.
29
+ - I recommend using IP-Adapter, however it reduces the effect of the mLORAs, so play with the strength. "Ease in out" weight type is a good starting point.
30
+
31
+ ## Examples
32
+
33
+ <video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-zoomin32.mp4" title="zoom in 32 frames"></video>