
XXOOM inspired style LoRA
How to use
Just prompt 1girl stuff as normal. This artist mainly draw themes containing busty dark-skinned and/or muscular females in little clothing and a lot of restraints so anything matching those tags should work fine. Clothed content works better than expected. For prompt suggestions see the sample images or the uploaded file with the training tags.
I recommend testing both Euler A and DPM++ 2M Karras samplers to see which one work best with your model. The former usually gives a more clean look while the latter a more drawlike style.
You can also try adding "3D" and/or "realistic" in negatives, especially if your model has some degree of realism mixed in.
Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<
MISC
Trained on AOM2 at 512px with 269 images.
All images are raw txt2img upscaled without inpainting or any helper embeddings.
描述:
Initial Release
训练词语:
名称: XXOOM Training Tags.zip
大小 (KB): 142
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: XXOOM.safetensors
大小 (KB): 36991
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success