Crane down LoRA for Wan2.1 14B I2V 480p

Overview

Moves the camera smoothly from a high angle downward, revealing subjects or settings with a cinematic descent. Ideal for dramatic entrances, scene introductions, or shifting focus from environment to character.This LoRA is trained on the Wan2.1 14B I2V 480p model.

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

Generate videos with 100+ Camera Control and VFX LoRAs on the Remade Canvas.
Discord: Join our community to generate videos with this LoRA for free

Prompt: The video shows an elderly man with a long white beard, glasses, and a work shirt working on radios on a wooden table in a workshop filled with vintage radios. The man is concentrating on fixing a radio. The cr4n3 crane down camera motion begins high, looking over the man's shoulder, slowly lowering the view to show him repairing the radio more closely, focusing on his hands. The camera continues to move downwards, getting closer to the radios on the table.

Prompt: The video focuses on a woman in a bathtub, seen from the chest up, with water reaching her nose. Her eyes are wide open, staring directly ahead. A cr4n3 crane down camera motion slowly lowers the perspective, and her hands reach out, slightly visible, toward the camera. The water gently ripples, creating a reflection.

Model File and Inference Workflow

📥 Download Links:

crane_down.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: cr4n3 crane down camera motion

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 crane down camera motion.
Epochs: 40

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!

Remade-AI
/

Crane-down