This LoRA is trained exclusively on the official webtoon series to faithfully capture its distinctive black and white manga/webtoon style, including clean linework, dramatic shading, and high-contrast ink aesthetic.

How to Use It Effectively

Trigger Word: DriftPixel_Burner

⚠️ Important: Do not use the trigger word by itself — results will be half-baked. Always combine it with detailed descriptions of pose, expression, outfit, lighting, and mood for the best quality.

Tip & Tricks!!

1. Strongest character fidelity
The model performs best when you include "simple background, white background" (or similar). These tags help the LoRA focus on the character.

Note: When using a plain background, always add lighting and shadow descriptions (e.g., dramatic shading, strong shadows, high contrast lighting), otherwise the image may look flat or incomplete.

2. Hair consistency
To better replicate her unique hairline and bangs, add bangs to your negative prompt. This helps avoid unwanted variations in the hair shape.


-- Supported Features --

Multiple outfits directly from the series
Various character modes: Normal, Enraged / Emptiness, Athena, and Rebirth

Note: Some modes (especially Athena and Rebirth) can be finicky and may require more specific prompting or higher LoRA weight.

For the best results with each mode and outfit, check the example prompts used in the showcase images (I won't list every possible tag here, but the samples show effective combinations).

Recommended Settings

• LoRA Weight: 0.9 – 1.2

• Sampler: Euler a (recommended) Alternative: DPM++ 2M Karras

• Scheduler: Normal or Beta 1.1

• Steps: 20 – 40

• CFG Scale: 5 – 7

• Resolution: 768×1024 (great starting point) I often use 832×1216

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

Bonus for ComfyUI Users

A full ComfyUI workflow is embedded in the metadata of every sample image I uploaded. Just download any showcase image and drag & drop it into ComfyUI — it will load the complete workflow automatically.

This LoRA represents many hours of careful training and testing. If you find it useful, please 👍 like, 💬 leave a comment with your results, and feel free to ⚡ tip. it really helps support future projects!