version 0.95

README.md

@@ -10,12 +10,13 @@ language:
 - [Basic camera motion LoRAs for Animatediff v2 motion models - version 1](#basic-camera-motion-loras-for-animatediff-v2-motion-models---version-1)
   - [Model Description](#model-description)
   - [File summary](#file-summary)
+  - [How to use](#how-to-use)
   - [General recommendation](#general-recommendation)
   - [Details and examples](#details-and-examples)
-    - [Walking front view](#walking-front-view)
-    - [Walking back view](#walking-back-view)
-    - [Walking right view](#walking-right-view)
-    - [Walking left view](#walking-left-view)
+    - [Zooming in](#zooming-in)
+    - [Zooming out](#zooming-out)
+    - [Lateral (horizontal) left](#lateral-horizontal-left)
+    - [Lateral (horizontal) rigth](#lateral-horizontal-rigth)
 
 # Basic camera motion LoRAs for Animatediff v2 motion models - version 1
 
@@ -34,6 +35,8 @@ This repository contains a collection of basic camera motion LoRAs finetuned on
 | 1600_cseti_9406077_camera-crane_down-10vid_mv2.safetensors    | v2                      | (3:2)         | 16     | 10           |
 | 1600_cseti_1720230_camera-crane_up-10vid_mv2.safetensors      | v2                      | (3:2)         | 16     | 10           |
 
+## How to use
+
 
 ## General recommendation
 - These are finetuned on a v2 model. They work also with AnimateLCM but don't work with v3 models
@@ -41,23 +44,32 @@ This repository contains a collection of basic camera motion LoRAs finetuned on
 - Animatediff v3 adapter LoRA is recommended regardless they are v2 models
 - If you want more motion try increasing the scale multival
 - I recommend using the above Base AR (Aspect ratio) for inference however they might work with other ARs too
-- Try playing with the lora strength and scale multival like increasing the scale multival and lowering the lora strength.
+- Try playing with the strength of
+  - motion LoRA 
+  - scale multival 
+  - v3_adapter lora
+  
+  like increasing the scale multival and lowering the lora strength.
 - 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.
 
 ## Details and examples
 
-### Walking front view
+### Zooming in
+- recommended strength: 0.8-1.0
 
-<video controls src="https://huggingface.co/Cseti/Walking_motion_LoRA_set_for_Animatediff_v2/resolve/main/LoRA-Comparison-upscaleAll-_00054.mp4" title="front view"></video>
+<video controls src="asset\LoRA-comparison-zoomin16.mp4" title="back view"></video>
 
-### Walking back view
+### Zooming out
+- recommended strength: 0.8-1.0
 
-<video controls src="https://huggingface.co/Cseti/Walking_motion_LoRA_set_for_Animatediff_v2/resolve/main/LoRA-Comparison-upscaleAll-_00063.mp4" title="back view"></video>
+<video controls src="asset\LoRA-comparison-zoomout16.mp4" title="zoom out"></video>
 
-### Walking right view
+### Lateral (horizontal) left
+- recommended strength: 0.8-1.0
 
-<video controls src="https://huggingface.co/Cseti/Walking_motion_LoRA_set_for_Animatediff_v2/resolve/main/LoRA-Comparison-upscaleAll-_00052.mp4" title="right view"></video>
+<video controls src="asset\LoRA-comparison-lateral_left.mp4" title="right view"></video>
 
-### Walking left view
+### Lateral (horizontal) rigth
+- recommended strength: 0.8-1.0
 
-<video controls src="https://huggingface.co/Cseti/Walking_motion_LoRA_set_for_Animatediff_v2/resolve/main/LoRA-Comparison-upscaleAll-_00048.mp4" title="left view"></video>
+<video controls src="asset\LoRA-comparison-lateral_right.mp4" title="right view"></video>