Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.
Join our Discord to generate videos of the Squish Effect LoRA for free.
Wan2.1 14B I2V 480p v1.0:
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.
The trigger word is: 'sq41sh squish effect'
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.
Recommended Settings:
LoRA strength = 1.0
Embedded guidance scale = 6.0
Flow shift = 5.0
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
Prompt Examples:
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.
Example 2: In the video, a miniature **** is presented. The **** is held in a person’s hands. The person then presses on the ****, causing a sq41sh squish effect. The person keeps pressing down on the ****, further showing the sq41sh squish effect.
As you can see, the prompt structure is identical, it is only the object being squished that changes.
Let me know if there are any questions, I'll be happy to help!