Mohit5899 commited on
Commit
6443d6d
·
verified ·
1 Parent(s): 23cf6d5

Create Read file

Browse files
Files changed (1) hide show
  1. Read file +28 -0
Read file ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wan2.1 14B I2V 480p v1.0:
2
+
3
+ Trained on 1.5 minutes of video comprised of 20 short clips of things being squished. This was trained on the Wan.21 14B I2V 480p model.
4
+
5
+
6
+ The trigger word is: 'sq41sh squish effect'
7
+
8
+ See below for some example prompts that have worked very well. I believe the prompt structure can be very similar as the examples are; you just need to specify the object being squished and that is the only difference.
9
+
10
+ Recommended Settings:
11
+
12
+ LoRA strength = 1.0
13
+
14
+ Embedded guidance scale = 6.0
15
+
16
+ Flow shift = 5.0
17
+
18
+ Here's a link to the Wan2.1 I2V inference workflow I used to generate these videos: https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_480p_I2V_example_02.json
19
+
20
+ Prompt Examples:
21
+
22
+ Example 1: In the video, a miniature rodent is presented. The rodent is held in a person’s hands. The person then presses on the rodent, causing a sq41sh squish effect. The person keeps pressing down on the rodent, further showing the sq41sh squish effect.
23
+
24
+ Example 2: In the video, a miniature tank is presented. The tank is held in a person’s hands. The person then presses on the tank, causing a sq41sh squish effect. The person keeps pressing down on the tank, further showing the sq41sh squish effect.
25
+
26
+ As you can see, the prompt structure is identical, it is only the object being squished that changes.
27
+
28
+ Let me know if there are any questions, I'll be happy to help!