Hugging Face's logo

Remade-AI
/
Jumpscare

Image-to-Video
Diffusers
English
text-to-image
lora
template:diffusion-lora
Model card Files
xet
 Community
1
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image, export_to_video

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-I2V-14B-480P,Wan-AI/Wan2.1-I2V-14B-480P-Diffusers", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Remade-AI/Jumpscare")

prompt = "The video shows a man with a slight smile, then the j432mpscare jumpscare occurs, revealing a distorted and monstrous face with glowing red eyes, filling the frame and accompanied by a loud scream."
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png")

image = pipe(image=input_image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

Jumpscare LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to Jumpscare your friends

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

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 shows a man with a slight smile, then the j432mpscare jumpscare occurs, revealing a distorted and monstrous face with glowing red eyes, filling the frame and accompanied by a loud scream.
Prompt
The video shows a person dressed in a white outfit with gold embellishments, gently touching the delicate pink flowers on a tree branch. The serene, peaceful atmosphere is further heightened by the soft-focus green foliage in the background. Suddenly, the j432mpscare jumpscare occurs and the tranquil scene is abruptly replaced by a monstrous creature's face, disrupting the serenity and replacing it with a sense of terror.

Model File and Inference Workflow

📥 Download Links:

Recommended Settings

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

Trigger Words

The key trigger phrase is: j432mpscare jumpscare

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 60 seconds of video comprised of 12 short clips (each clip captioned separately) of jumpscares.
  • Epochs: 35

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!

Downloads last month
27
Inference Providers NEW
Image-to-Video
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Remade-AI/Jumpscare

Base model

Wan-AI/Wan2.1-I2V-14B-480P
Adapter
(113)
this model

Collection including Remade-AI/Jumpscare