Crush Effect LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to crush any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

Features

• Transform any image into a video of it being crushed
• Trained on the Wan2.1 14B 480p I2V base model
• Consistent results across different object types
• Simple prompt structure that's easy to adapt

Community

• Discord: Join our community to generate videos with this LoRA for free
• Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!

Prompt

The video begins with a tank. A hydraulic press positioned above slowly descends towards the tank. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the tank, causing the tank to collapse inward until the tank is no longer recognizable.

Prompt

The video begins with a man. A hydraulic press positioned above slowly descends towards the man. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the man, causing the man to collapse inward until the man is no longer recognizable.

Prompt

The video begins with a chicken. A hydraulic press positioned above slowly descends towards the chicken. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the chicken, causing the chicken to collapse inward until the chicken is no longer recognizable.

Prompt

The video begins with a coke. A hydraulic press positioned above slowly descends towards the coke. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the coke, causing the coke to collapse inward until the coke is no longer recognizable.

Model File and Inference Workflow

📥 Download Links:

• crush_20_epochs.safetensors - LoRA Model File
• wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

---

Recommended Settings

• LoRA Strength: 1.0
• Embedded Guidance Scale: 6.0
• Flow Shift: 5.0

Trigger Words

The key trigger phrase is: c5us4 crushes it

Prompt Template

For best results, use this prompt structure:

The video begins with a [object]. A hydraulic press positioned above slowly descends towards the [object]. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the [object], causing the [object] to collapse inward until the [object] is no longer recognizable.

Simply replace [object] with whatever you want to see crushed!

ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

• Base Model: Wan2.1 14B I2V 480p
• Training Data: Trained on 1.5 minutes of video comprised of 20 short clips (each clip captioned separately) of things being crushed by a hydraulic press
• Epochs: 20

Additional Information

Training was done using Diffusion Pipe for Training

Acknowledgments

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!