This is an experiment to train a LoRA for video, turns out for transformation only High Noise needs training for WAN. Wanted to have something that doesn't have the unwanted motion, pose changes and disappearing clothes of existing LoRAs. Sadly clothes still have a tendency to disappear
Description
for Wan 2.2 Image-to-Video, High Noise only. by default it produces real bodybuilder sizes. you need to add more muscle descriptors to increase the size
FAQ
Comments (5)
prompt tips or trigger word? thanks!
muscle mass increases. like her/their/the muscle mass increases. its in the description
really fun to use👍
thanks, if you make more, feel free to post them
Excellent model/workflow.
Details
Downloads
290
Platform
CivitAI
Platform Status
Available
Created
4/28/2026
Updated
5/28/2026
Deleted
-
Trigger Words:
muscle mass increases
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.