models/[SDXL] Darkness / 暗闇化 - v2.0

[SDXL] Darkness / 暗闇化 - v2.0

|
9/26/2025
|
6:01:39 PM
| Discussion|
0
Dark-skinned female elf with gradient purple eyes and long braided ponytail wears a white hooded cloak and carries a scabbard, standing against a mossy stone wall illuminated by warm dappled light.
A dark fantasy scene depicting an elf girl holding a torch inside a dim cave, sitting with a scared expression, accompanied by a glowing-eyed skeleton behind her.
Close-up view of a dark fantasy girl with pale pink hair and short white horns, holding an iridescent flower in front of her face under dramatic volumetric lighting.
A girl with green gradient eyes, long dark hair in a low ponytail with a hair ribbon, wearing a sleeveless black tank top, orange shorts, and black high heels, caught midair as she loses balance and falls inside a room illuminated by cinematic volumetric lighting and dappled light filtering through sheer curtains, surrounded by potted plants and dramatic shadows.
Anime-style girl with white hair and rectangular glasses wearing a spaghetti strap dress, looking up under a starry night sky over a field of white flowers.

Recommended Prompts

darkness,dark sky,glowing eyes

masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, 1girl, solo, night, darkness

Recommended Negative Prompts

lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, poorly drawn, blurry, ugly, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face

Recommended Parameters

samplers

Euler a, DPM++ 2M SDE

steps

40

cfg

5 - 7

clip skip

2

resolution

768x1152, 1152x768

other models

darkness_xl_v20 (cd20ac3d70b9), illustriousPencilXL_v320 (446a64d62c), IllusionBreed_v30 (f523fed4cf), VioletBreed_v20 (ad2bb63e0b), IllusionBreed22D_Slender_v30 (4283f4aaa5), Illustrious-XL-v1.0 (735cf3fefc), RoseBreed_v10 (94d787e776), IllusionBreed22D_v50 (ef16ea6ac2), darkness_xl_v10 (ca492996c9ec)

Tips

Enable the LoRA and adjust the weight up to around 2.0 to control the level of darkness.

Add prompts like 'darkness' or 'dark sky' to improve dark scene rendering.

Add 'glowing eyes' prompt to make character eyes glow.

Some sample images use the NegPiP extension for negative prompt weights.

Version Highlights

Both compatible with Illustrious(0.1/1.0) and Pony checkpoints

Creator Sponsors

Check out more SD1/SDXL LoRA and checkpoints by JujoHotaru on HuggingFace repository and CivitAI models list.

SD1 version is also available at CivitAI model page.

(日本語説明は後半にあります)

The popular "Hotaru's LoRA series" (for SD1) is now available for SDXL! More will be released gradually on CivitAI (already available on HuggingFace).

Using only prompts, it is difficult to render characters and backgrounds as dark while keeping only light sources bright (such as lamps, the moon, and stars). This LoRA enables to generate such images.

This LoRA is compatible with Pony / Illustrious based checkpoints since v2.0. Some checkpoints may have less compatibility.

This LoRA is mainly tested on 2D-2.5D illustrations, and may not suitable for photorealistic checkpoints.

My "Breed" series checkpoints will make good outputs. Sample images are generated with "Breed" series listed on "Suggested Resources" section.

SD1 version is also available.

Usage

It works simply by enabling the LoRA, so basically no additional prompts are necessary. But adding prompts such as darkness or dark sky to indicate darkness can lead to better results.
If you want to make the character's eyes glow, add glowing eyes.
The level of darkness can be adjusted by the LoRA weight. For a darker effect, increase the weight. The upper limit is around 2.0.


More various other SD1/SDXL LoRA's and checkpoints are available on my HuggingFace repository or CivitAI models list. Please check it out.

CAUTION : Some sample images' prompt is using NegPiP extension for minus weight.


SD1でご好評いただいていた十条蛍のLoRAシリーズが、SDXL対応になって再登場します。HuggingFaceで先行公開中ですが、CivitAIにも順次掲載していきます。

キャラクターや背景を暗くしつつ、灯具や月・星など光源部分だけ明るく描写する、というのはプロンプトだけでは難しいですが、本LoRAを用いることで出力できるようになります。

v2.0からはPony系・Illustrious系のデータモデルに対応しています。一部のデータモデルでは、うまく再現されないことがあります。

2D・2.5Dイラスト系のデータモデル用で主にテストされており、実写系での効果については未確認です(使うことはできるようです)。

拙作データモデル「Breedシリーズ」と組み合わせると、高い効果を発揮します。サンプル画像もBreedシリーズ("Suggested Resources"セクションに掲載)で生成されています。

SD1系対応バージョンも公開しています。

使い方

LoRAを有効にするだけで発動します。階層調整済みですので、基本的には階層指定せず強度指定のみで大丈夫です。
必須ではありませんが、darknessdark skyなど暗さを示すプロンプトを追加すると効果が高まります。
キャラクターの目を光らせる場合はglowing eyesを追加してください。
LoRA適用強度で暗さを調整できます。より暗くするには強度を上げてください。上限は2.0くらいになります。


他にもさまざまなSD1/SDXL用LoRAおよびデータモデルを公開していますので、HuggingFaceリポジトリまたはCivitAIの配布モデルリストをご覧ください。

掲載しているサンプル画像のプロンプトの一部では、NegPiP拡張機能を使ったマイナス強度指定を使用しています。

Previous
Faceless Gods - Flux
Next
👑✨ TrendCraft: The People’s Style Detailer 🚀⭐Noob/Illustrious Base 🎨 - v2.3I Illustrious 4/15

Model Details

Model type

LORA

Base model

Illustrious

Model version

v2.0

Model hash

34f55d21a6

Creator

Discussion

Please log in to leave a comment.

Model Collection - [SDXL] Darkness / 暗闇化

Images by [SDXL] Darkness / 暗闇化 - v2.0

concept Images

effect Images

lora Images

sdxl Images