đ Crash zoom in LoRA for Wan2.1 14B I2V 480p
This LoRA can abruptly zoom in on the subject, typically the face, to heighten drama, surprise, or comedic timing. It's ideal for stylized edits, reaction shots, or sudden emotional emphasis.
đ Quick Start
Model Information
| Property |
Details |
| Model Type |
Crash zoom in LoRA for Wan2.1 14B I2V 480p |
| Base Model |
Wan-AI/Wan2.1-I2V-14B-480P, Wan-AI/Wan2.1-I2V-14B-480P-Diffusers |
| Pipeline Tag |
image-to-video |
| Tags |
text-to-image, lora, diffusers, template:diffusion-lora, image-to-video |
Example Widgets
- Example 1
- Text: A man with short brown hair wearing a white shirt and a dark coat stands in the red neon light of a motel room doorway. He looks back towards the motel room. The camera performs a cr34sh crash zoom in effect, rapidly zooming closer to the man's face. He turns with a shocked expression, as if he heard a noise, and reaches for his pocket.
- Output: example_videos/1.mp4
- Example 2
- Text: A young woman with red hair in a ponytail, wearing a t - shirt and jeans, sits in a wooden chair, facing away from the camera, in a room filled with dozens of old CRT televisions, each displaying different images. The camera performs a cr34sh crash zoom in effect, rapidly zooming closer to the woman's face as she turns her head, looking directly at the viewer with a mixture of curiosity and confusion. The image on the central TV begins to change, reflecting the scene.
- Output: example_videos/2.mp4
⨠Features
- Trained on the Wan2.1 14B 480p I2V base model.
- Consistent results across different object types.
- Simple prompt structure that's easy to adapt.
đĻ Installation
Download Links
đ Documentation
Recommended Settings
- LoRA Strength: 1.0
- Embedded Guidance Scale: 6.0
- Flow Shift: 5.0
Trigger Words
The key trigger phrase is: cr34sh crash zoom in effect
Prompt Template
For prompting, check out the example prompts; this way of prompting seems to work very well.
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 50 seconds of video comprised of 10 short clips (each clip captioned separately) of scenes that used the crash zoom in camera motion.
- Epochs: 30
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!
đ License
This project is licensed under the Apache - 2.0 license.
đ Community
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers