Tensor.Art
Create

Wuthering Waves - Taoqi | [3xIMG-AT-SDXL]

LORA
Original

Updated:

vA0_34HQE6
v0.1_E10
v0.1_E08
368

Taoqi of Wuthering Waves

Trained with in-game screenshot of Taoqi and manually cropped to match Tensor Trainer's img size for SDXL training and tagged with auto tagging feature. Tagging focused on subject only (both v0.1 versions) and with simple background (34HQE6).

Base training model is AnimagineXL V3 (both v0.1) and AnimagineXL v3.1 (for 34HQE6) 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.

Download available for vA0_34HQE6! Feel free to grab it and test locally.

Thank you for choosing this LoRA on your image generation.

Version Detail

Trained by Tensor
SDXL 1.0
6
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

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.