A LoRa for generating confused looking anime girls with interrogation marks on their heads.

To see all my LoRAs, please (temporarily) disable X and XXX visibility, otherwise a lot will be hidden at the whims of credit card companies. You can help support making models like this by posting stuff you've made with it to the gallery using the "add post" button, that helps me earn back the training cost at no cost to you.

V2:

Trigger: C_L_A_G
Pick one: ? or ??
Negative if using ?: ??
Pick one or both: confused, thinking
Optional: | |, dot eyes, looking at viewer, head tilt

Gave tags a second pass (cleaning up a lot of garbage and consistently applying "?" versus "??" and camera so those should work better), cleared alpha channels, and removed a duplicate image. Was just going to make an Anima port till I saw how rough the original dataset was.

V1:

The PDXL version won my poll on what to convert to ILXL, so it's my first LoRA of 2025.
New for ILXL: “dot eyes” and “blank eyes” were added to applicable training data that didn’t have it.

Tags: clagwimoth, confused, ?, portrait,
Optional: | |, dot eyes, looking at viewer, blank eyes

Was pretty solid from epoch 1, which is expected since the PDXL version worked that well and the concept is handled decently without a LoRA.