models/Tangbohu Detail Tweaker LoRA (唐伯虎细节调整LoRA) - v1.0

Tangbohu Detail Tweaker LoRA (唐伯虎细节调整LoRA) - v1.0

|
8/16/2025
|
11:07:27 PM
| Discussion|
0
Portrait of a determined military commander with ginger hair and blue eyes wearing an elegant, gold-accented navy uniform blending Napoleonic era and cyberpunk styles, standing in a smoky urban stronghold.
A detailed portrait of a hooded vampire woman with freckles, jade eyes, and braided light brown hair standing in a misty moonlit cemetery with an eerie atmosphere.
A detailed portrait of a freckled elven hemomancer woman wearing a scarlet hood and robes, with blood-red eyes and intricate magical symbols swirling in a dark forest cave.
Anime girl with an eye patch in a red traditional Chinese dress and a black jacket, standing by a cherry blossom branch, AI generated image using Stable Diffusion.
Moody portrait of a young woman in a black sleeveless turtleneck, generated using Stable Diffusion AI

Recommended Negative Prompts

EasyNegative, nude

Recommended Parameters

samplers

Euler a

steps

30

cfg

7

resolution

768x768

other models

lyriel_v15 (4d91c4c217), tangbohu 2D mix (8e1cb91487), braBeautifulRealistic_brav5 (ac68270450), breakdomainanime_A0440 (f1c731fd51), deliberate_v2 (9aba26abdf)

Tips

Increase LoRA weight to enhance details, up to a maximum of 3.

Reduce LoRA weight (negative weights) to reduce details, down to a minimum of -3.

Larger weights may cause significant changes in the image.

Trained with a larger dimension (dim) to provide more diversity.

This is a LoRA for enhancing/reducing details while maintaining the original image as much as possible; It is suitable for various basic models (including animation and realistic models)/style LoRA/character LoRA, etc.

Increase weight to increase details, reduce weight to reduce details, up to a maximum/minimum of 3/-3!

When using larger weights, there may be significant changes in the image

A larger dim was used for training to provide more diversity.

Attention: Use negative weights to reduce details!

这是一个LoRA,用于增强/减少细节,同时尽量保持原图;它适用于各种基础模型(包括动画和写实模型)/风格LoRA/角色LoRA等。

增加权重增加细节,减少权重减少细节,最高/最低可达3/-3!

使用较大权重的时候画面有可能会产生比较大的变化

使用了较大的dim进行训练来提供更多的多样性。

注意:使用负权重来减少细节!

ツイッターで助けてくれた日本人の友人に感謝して、ありがとう!!

Contributor

Previous
Geometric design style几何设计风格lora - v1.0
Next
GENESIS - v0.2

Model Details

Model type

LORA

Base model

SD 1.5

Model version

v1.0

Model hash

e73c2f2dd4

Creator

Discussion

Please log in to leave a comment.

Model Collection - Tangbohu Detail Tweaker LoRA (唐伯虎细节调整LoRA)

Images by Tangbohu Detail Tweaker LoRA (唐伯虎细节调整LoRA) - v1.0

style Images