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

Overview

Lifts the camera smoothly upward to reveal a scene from above. Ideal for grand reveals, transitions, or adding cinematic elevation to a moment.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: A woman in a white dress is walking across a large, reflective body of water with mountains in the background. The words "REMADE" are etched into the surface near the water. The cr4n3 crane up effect is applied, smoothly lifting the camera's viewpoint higher, revealing more of the surrounding landscape, including the shoreline and the vast expanse of water ahead as the woman continues walking into the distance.

Prompt: Six monks in orange robes walk in a line along a stone path towards a large temple complex shrouded in mist. The scene is captured with a cr4n3 crane up effect, smoothly rising, revealing more of the temple's architectural details and the expanse of the courtyard as they continue to walk towards the temple in the distance.

Prompt: In a dark, cavernous room, a young woman with red pigtails sits in a wooden chair, facing a wall of vintage televisions, each displaying a different moving image. The woman turns her head toward one of the screens, and then the cr4n3 crane up effect begins, smoothly lifting the camera's viewpoint higher. As the cr4n3 crane up effect continues, more of the room and the wall of televisions displaying varied scenes become visible, with the programs on the television screens reflecting off the wet floor.

Model File and Inference Workflow

📥 Download Links:

Crane_up.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 up 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 crane up 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!

Remade-AI
/

Crane_up