Hanfu - Blue Water Peacock

0
0
0
0
RealisticChinese StyleFashion & MakeupGirlElement BoostClothing
최근 업데이트: 첫 번 게시:
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info
Realistic,Chinese Style,Fashion & Makeup,LoRA,SD 1.5Image info

Model Introduction:

This is a Lora model trained on materials generated based on MJv6! The main effect is the combination of underwater photography with colorful Hanfu clothing!!

For specific usage instructions, please refer to the example image!!


Recommended Parameters:

Large model:Maiguo Realistic v7

VAE:Realism 840000

CLIP Skip: 1

Recommended positive tags: None

Recommended negative tags: logo, text, badhandv4, EasyNegative, ng_deepnegative_v1_75t, bad_prompt Negative Embedding_v2.0, bad image repairing veryBadImageNegative_veryBadImageNegative_v1.3, negative_hand-neg, mutated hands and fingers, poorly drawn face, extra limb, missing limb, disconnected limbs, malformed hands, ugly,

Lora weight: 0.6-0.9

Iteration steps: 20-30    

Sampling recommendation: DPM++2M Karras

Resolution:512*1024 (Important!!)


Finally:

Generally direct output, 3-5 images will look good, of course, it also tests your cue words, if you feel the facial effect is poor, you can enable ADetailer.

Wish you all have fun, welcome to test and return images!!


Version 2.0 will improve eye issues!!

토론

가장 인기
|
최신
보내기
곧 오픈
다운로드
(0.00KB)
자세히
유형
온라인 생성 횟수
0
다운로드
0
추천 매개변수
추천 체크포인트 조합Checkpoint
없음
추천되는 체중
0.8
CFG
7
VAE
없음

갤러리

가장 인기
|
최신