Zalecane podpowiedzi

intricate, elegant, sharp focus

Zalecane negatywne podpowiedzi

lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature

Zalecane parametry

samplers

DPM++ 2M SDE, DPM++ 3M SDE, DPM++ 2M SDE Karras, DPM++ SDE Karras

steps

40 - 60

cfg

4 - 6

Wskazówki

Use main model 1.2 with weight between 0.1 and 0.8 and add MJ52_v2.0 with weight between 0.3 and 1 to supplement micro details.

The v1.2 model acts as color enhancer, background depth improver, and composition improver.

The v2.0 model acts as a detail tweaker adding micro details.

Najważniejsze informacje o wersji

1.2 version
more accurate, improve BG depth

MJ52_v2.0 is a continuation of main model 1.2, they complement each other, using two versions at the same time you will get stunning results. Use v1.2 with 0.1 - 0.8 of weight and add v2.0 to additional micro details with 0.3 - 1 of weight.
best with DPM++ 2M SDE, DPM++ 3M SDE
LoRa mimicking midjourney slyle v5.2 This LoRA works as:
v.1.2 - Color enhancer (adds contrast and colors)
v.1.2 - BG depth improver (adds depth on the background)
v.1.2 - Composition improver (change composition)
v.2.0 - Detail tweaker (make little changes and supplements the picture with MICRO details)

CFG Scale 4 - 6.
Use v1.2 with 0.1 - 0.8 of weight and add v2.0 to add micro details with 0.3 - 1 of weight.

Współtwórca

Poprzedni
Cinematic Shot✨ - FLUX v1.0
Następny
748cm | Style for Illustrious/NoobAI 0.75 - v1.0

Szczegóły modelu

Typ modelu

LORA

Model bazowy

SDXL 1.0

Wersja modelu

v1.2

Hash modelu

e526855052

Twórca

Dyskusja

Proszę się log in, aby dodać komentarz.