A LoRa for generating confused looking anime girls with interrogation marks on their heads. <a rel="ugc" href="https://civarchive.com/models/950882/confused-looking-anime-girls-with-interrogation-marks-on-their-heads">The PDXL version</a> 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 eyesWas pretty solid from epoch 1, which is expected since the PDXL version worked that well and the concept is handled decently without a LoRA.

[IL] Confused looking anime girls with interrogation marks on their heads

“dot eyes” and “blank eyes” were added to applicable training data that didn’t have it.

1227643_training_data.zip

ILXL_Confused_looking_anime_girls_with_interrogation_marks_on_their_heads-000013.safetensors

[ILXL] Confused looking anime girls with interrogation marks on their heads

A LoRa for generating confused looking anime girls with interrogation marks on their heads. <a href="https://civitai.com/models/950882/confused-looking-anime-girls-with-interrogation-marks-on-their-heads" rel="ugc noopener noreferrer nofollow" target="_blank">The PDXL version</a> 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 eyesWas pretty solid from epoch 1, which is expected since the PDXL version worked that well and the concept is handled decently without a LoRA.

&lt;p&gt;“dot eyes” and “blank eyes” were added to applicable training data that didn’t have it.&lt;/p&gt;

Files with SHA256: 3d0b50b01cf7d4f865dfb0404bd49e3195f8d2f3b092df9f82b0217a01e14142