There are 4 versions because each one works a little different and has pros/cons.
v1's Post has images for all 4 versions.
Please see the last images in v1's post to find grids of version differences.
I accept Lora requests: https://civitai.com/articles/1178
Weight: 0.9
Trigger: Poncho <-- Same as the Lora file name, isn't that easy to remember?
Extra prompts: none
V1 : Trained on 9 images
V2 : Trained on 26 images
V3 : Trained on 23 images
V4 : Trained on 31 images