Sign In

DollyZoom-Wan2.2/2.1-I2V-A14B

106

1.3k

0

63

Updated: Aug 7, 2025

action

Verified:

SafeTensor

Type

LoRA

Stats

716

0

234

Reviews

Published

Jul 9, 2025

Base Model

Wan Video 14B i2v 720p

Training

Epochs: 240

Trigger Words

dolly-zoom shot
the subject of the shot maintains the same size in the frame while the background appears to stretch

Hash

AutoV2
ECD8D7BDE4

DollyZoom-Wan2.2-I2V-A14B. You can use MediaInfo to check the generation info in the video. The workflow I used is the official one but adding sage attention and LoRAs after loading the ckpt. If you love my lora, you can buy me a coffee : https://ko-fi.com/ghostshell .

UPDATE VERSION-Wan2.2

This LoRA is for high noise. I trained LoRA for high and low , but I found the high version is enough for generating the dolly zoom effect. The Image below contains the Workflow.

VERSION-Wan2.1

You can use MediaInfo to check the generation info in the video. The workflow I used ComfyUI-WanVideoWrapper. I uploaded an article of my experience of training Wan2.1 LoRA (Both I2V & T2V): My Personally Training Experience of WAN:Starting with Data.