Arc shot LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model.Moves the camera in a smooth, curved path around the subject, adding depth and cinematic motion. Ideal for dramatic reveals or emotional emphasis.

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 young Black man wearing a grey baseball cap, a gold chain, and a black shirt stands in a recording studio, singing into a microphone. The background features a neon sign that says "REMADE" and a red couch. The 34Ar2c arc the camera moves in a smooth curve around the man, shifting the perspective around him as he performs with passion.

Prompt: A woman with dark hair executes a high kick, kicking up water droplets, against a futuristic man in a mask, in a neon-lit cyberpunk street. The 34Ar2c arc the camera moves in a smooth curve around the two fighters, revealing more of the scene and their confrontation.

Prompt: An elderly woman with white hair and sunglasses is seated on a subway train. She wears a dark coat and is lighting a cigarette with a match while reading a book. The 34Ar2c arc the camera moves in a smooth curve around the woman, showing her from different angles as she reads.

Model File and Inference Workflow

📥 Download Links:

Arc_shot.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: 34Ar2c arc the camera moves in a smooth curve around

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 arc shots.
Epochs: 15

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
/

Arc_shot