Taoqi of Wuthering Waves
Trained with in-game screenshot of Taoqi and manually cropped to match online trainer img size for SDXL training and tagged with auto tagging feature.
Base training model AnimagineXL v3.1 so you can use its recommended generation parameter, but you can also try it with other XL model. Keep in mind that this is only for XL and NOT for Pony.
Updates to this will be solely focused on better tagging (and perhaps trying to enhance my dataset) since this is my very first time of doing LoRA things.
Thank you for choosing this LoRA on your image generation.
Description
Known issue:
Sitting with crossed legs still have deformities.
Posing isn't really flexible and may look stiff.
Default outfit still has inaccuracies.
Her hair ornament sometimes not shown. Use "hair ornament" in prompt as a workaround.
Eye color inconcistency (sometimes purple, sometimes pink) due to my fault in thinking that she has pink eyes.
Most likely bad at NSFW since I don't have the dataset for that.
Your generation results may look like the in-game graphics of Wuthering Waves (not necessarily bad, but may ruin your desired style).
You tell me