models/Dark & Eerie 1.0 - Dark&Eerie v1.0

Dark & Eerie 1.0 - Dark&Eerie v1.0

|
7/29/2025
|
3:28:01 AM
| Discussion|
0
A dreamy photorealistic portrait of a young pale woman with soft wavy white hair and clear grey eyes, framed by softly blurred black flowers against a moody black background.
Surreal portrait of a young woman with voluminous black hair, face covered in textured cosmic glitter blending vibrant pink and green iridescent pigments, glowing light green eyes, and dark lips, wearing a seamless black garment fading into a dark gray-blue background speckled with tiny scattered lights.
A high-contrast portrait of a man with pale skin partially covered in a glossy black substance, shaved hairline, looking downward with a contemplative expression against a soft gray background.
Eerie portrait of a young woman with a platinum blonde bob haircut and light blue eyes, wearing a sheer black turtleneck against a vibrant teal background.

Recommended Parameters

samplers

DDIM Trailing, DPM++2M Trailing, Euler A Trailing, DPM++2M AYS, DDIM

steps

50

cfg

2 - 2.8

resolution

896x1152

Tips

Use long, descriptive prompts to maximize model effectiveness.

LoRA weight should be between 0.6 and 0.8; above 0.8 introduces more grain.

Enable TeaCache with parameters 4-48, 0.30, 8 to speed up generation.

Shift value depends on output size, e.g., 3,12 for 896x1152px.

Version Highlights

1.0 Initial Release.

Trigger: bsflash_eerie.

Dark & Eerie 1.0 FLUX.1

This LoRA enhances portraits with an unsettling aesthetic and a touch of darkness. It replaces the standard FLUX face with a more ethereal look, and provides a wider range of "edgy" haircuts and alt-fashion styles. The style spans from the uncanny to the eerie, culminating in horror.

For optimal results, use long, descriptive prompts, as shorter ones may reduce its effectiveness.

Trigger Word: bsflash_eerie.

If you're using DrawThings, simply drop example images onto the canvas to generate the exact image with the corresponding metadata.

Settings:

- LoRA Weight: 0.6 - 0.8 beyond 0.8 the images introduces more grain.

- Sampler: DDIM Trailing* / DPM++2M Trailing* / Euler A Trailing* or DPM++2M AYS.

*Trailing is similar to the Uniform scheduler in case you don't have it.

- Steps: 50 with enabled TeaCache: 4-48, 0.30, 8 to speed up the generation.

- Text Guidance / CFG: 2 - 2.8

- Shift: depending on the output size. For 896x1152px = 3,12

Comparison (Style Prompt):

Comparison (Generic Prompt):

Sampler Examples:

Contributor

Previous
Animij - v3.0
Next
Pie - Models 🥧 - Apple Pie

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

Dark&Eerie v1.0

Model hash

35a0d4f30d

Creator

Discussion

Please log in to leave a comment.

Images by Dark & Eerie 1.0 - Dark&Eerie v1.0

dark Images

eerie Images

goth Images

style Images