💖 Support My Work & Explore More

If this model is useful to you, your support helps me keep publishing free models and open-source AI tools.

• Patreon: Support on Patreon

• Ko-fi: Buy me a Ko-fi

• Buy Me a Coffee: Buy me a Coffee

Discover more of my models, projects, and practical AI resources:

• Portfolio: artificialguy.com — models, projects, and experiments.

• Prompt library: FindGoodPrompt — curated prompts for image and language models.

• AI tools directory: JustGoodAI — a curated directory of useful AI tools.

• Twitter/X: @artificialguybr — new models announced here first.

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.

Spontaneous Combustion LoRA for Wan I2V

Model Description

This LoRA specializes in creating dramatic spontaneous combustion effects from static images. Transform ordinary objects into scenes of sudden, mysterious ignition with realistic fire propagation, smoke, and ember effects. Perfect for creating suspenseful, supernatural, or dramatic moments in your videos where objects burst into flames without any external trigger.

Trigger Words

The trigger phrase is Spontaneous Combustion.
For best results, use “Spontaneous Combustion” in your prompt when describing the scene you want to animate. The model will transform your static image into a dynamic combustion sequence.

Setup for ComfyUI

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

• Download [WAN2.2]Spontaneous_Combustion_Redmond_low_noise.safetensors and [WAN2.2]Spontaneous_Combustion_Redmond_high_noise.safetensors and place them in ComfyUI/models/loras/
  Ensure your ComfyUI environment is already configured to run Wan I2V models.

  Example Workflow (ComfyUI)

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

• Load your base Wan I2V model.

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

• Select either [WAN2.2]Spontaneous_Combustion_Redmond_low_noise.safetensors and [WAN2.2]Spontaneous_Combustion_Redmond_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).