DCUSA | Style LoRA

DCUSA | Style LoRA

Issa new LoRA! Trained to create images in the style of DCUSA.

• Trigger Word: dcusastyle

• Recommended Weight: 0.8 - 1.0 Lower weights lean more subtle and soft, higher values emphasize facial style and body definition.

• Additional Tags: adult, bara, muscular

Training Details

• Dataset of 225 manually curated, decensored and de-watermarked images

• I did my best to remove as many speech bubbles and texts as possible (98% success!)

• Tags were generated with a mix of automated and manual annotation

• All sample images shown are generated in ComfyUI with a hires-fix pass (no inpainting or Adetailer)

Usage Notes

• Works well with muscular and adult-themed prompts; add bara in your positive prompt if you want beefier results

• To reduce unwanted generations, add child, shota to your negative prompt

• NSFW material is part of the dataset. Safe outputs can be achieved by steering prompts away from NSFW content

Please follow the CivitAI Content Policy when using this model.