Trained on the official webtoon series and meant to replicate that black and white style.

Tip & Tricks!!

1. Since this LoRA was trained on the webtoon alone, this mean that it tend to generate the strongest character when using "simple background, white background" tags... so i recommend to utilise them if you only care about the character.

Note: if you use this tags you need to also mention the light and shadow, otherwise the generation will be half-baked.

2. If you want to have more consistent hair, i recommend to add "bangs" in the negative prompt... to get her unique hair line.


ADDITIONAL INFO:
- Supports multiple outfits straight from the series!
- Supports multiple modes of her: Normal, Enraged/Emptiness, Athena and Rebirth 

Note: Some of them are really finicky to utilise.

Check out the prompts i utilise in creating the showcase images, because i won't list every possible tag that i utilise.

Settings i usually use:

• LoRA Weight: 0.9 – 1.2

• Sampler: Euler a (or DPMPP_2M + Karras if backgrounds break)

• Scheduler: Normal or beta_1_1

• Steps: 20–40

• CFG Scale: 5–7

• Resolution: 768×1024 (good starting point, i'm using 832 x 1216)

Trigger Word: DriftPixel_Burner

Do NOT use the trigger word alone, results will be half-baked. Be very specific and descriptive in your prompt for best quality.

Recommended Universal Negative Prompt:

low quality, worst quality, blurry, jpeg artifacts, bad anatomy, bad hands, deformed, distorted, disfigured, extra limbs, missing limbs, malformed limbs, fused fingers, too many fingers, mutated hands, poorly drawn hands, poorly drawn face, long neck, gross proportions, cropped, out of frame, watermark, text, signature, logo, username

ComfyUI Workflow Included!

Download any sample image I uploaded and drag & drop it into ComfyUI — it should load the full workflow from metadata.

This represents many hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip!