Special Thanks: This project was made possible thanks to generous sponsorship and GPU time provided by Redmond Ai. We are grateful for their support in training this LoRA.

Fish Eye LoRA for Wan

Model Description

This LoRA specializes in creating stunning fish-eye lens effects that add a unique wide-angle distortion to your videos. The fish-eye effect creates a characteristic convex, non-linear view that gives scenes a distinctive curved appearance, with the center appearing closer and the edges more distorted. Perfect for artistic, experimental, or dramatic visual storytelling.

Trigger Words

The trigger phrase is Fish eye effect.
For best results, use “Fish eye effect” at the end of your prompt when describing a scene. The model will render your scene with the characteristic wide-angle distortion of a fish-eye lens.

Setup for ComfyUI

To use this LoRA in ComfyUI, simply place the files in your loras directory:

• Download both Fish Eye_low_noise.safetensors and Fish Eye_high_noise.safetensors and place them in ComfyUI/models/loras/
  Ensure your ComfyUI environment is already configured to run Wan models.

  Example Workflow (ComfyUI)

  In your ComfyUI workflow, add a Load LoRA node after your base model loader.

• Load your base Wan model.

• Connect the output of the model loader to the model input of the Load LoRA node.

• Select both Fish Eye_low_noise.safetensors and Fish Eye_high_noise.safetensors in the Load LoRA node.

• Connect the MODEL output of the LoRA node to your KSampler.

• Adjust the strength_model as needed (0.8-1.0 is a good starting point).

  Example Prompts

  Here are some example prompts to get you started with Fish Eye:

• A dancer leaping in slow motion under stage lights. Fish eye effect.

• A person opening an old book as dust floats up. Fish eye effect.

• A child blowing giant soap bubbles. Fish eye effect.

• A cyclist crossing a narrow wooden bridge. Fish eye effect.

• A man with a cat. Fish eye effect.

​