Cz艂onkostwo PixAI
PixAI
PixAI
Generate
Sign in
Strona g艂贸wna
Generowanie
Modele
Studio
NEW
Konkurs
Utw贸rz z Mio.2
Skrzynka narz臋dziowa
NEW
Guide

SD

馃毀 DarkAngel-Mix [2D]

Tw贸rz

  • Generator obraz贸w AI
  • Generator animacji AI
  • Skrzynka narz臋dziowa
  • Generatory tematyczne
  • Trenuj LoRA
  • Agent Mio.2
  • Studio

Odkrywaj

  • Popularne tagi
  • Ranking
  • Rynek Modeli
  • Konkurs
  • Aktualno艣ci

O nas

  • Guide
  • Jak u偶ywa膰 PixAI
  • Tsubaki.2
  • Poznaj Mio
  • Zasady tre艣ci

Cennik i pomoc

  • Cz艂onkostwo
  • Pakiety kredyt贸w
  • Kontakt

Aplikacja mobilna

  • Pobierz aplikacj臋 PixAI
  • App Store
  • Google Play
漏 2026 PixAI
  • Regulamin
  • Polityka prywatno艣ci
  • Polityka praw autorskich
  • Attributions
  • Ustawa o Okre艣lonych Transakcjach Handlowych
馃毀 DarkAngel-Mix [2D] - AI Model cover image
Przes艂ano
9 lip 2024, 17:48
U偶ycia
3.9k
Opinie
Doskona艂y聽 (1)
Kroki pr贸bkowania

26

Metoda pr贸bkowania

Euler a

Skala CFG

6

Niepo偶膮dane

(bad-artist-anime, by bad-artist:1.4), (worst quality, low quality:2), (bad quality:1.9), normal quality, (EasyNegativeV2, easynegative:1), (bad eye, unclear eyes, undetailed eyes, missing limbs, fused limbs, broken limbs, fewer digits, extra digits, mutation, deformity:1.4), (interlocked fingers:1.3), (bad anatomy:1.1), monochrome, watermark, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (white background, simple background:1.3), (NSFW, cleavage:1.3)

Uprawnienia
  • Allow image generation & sharing
  • Zezw贸l u偶ytkownikom pobiera膰 Tw贸j model
  • Zastosowania komercyjne

Opis

Recommended: 20 steps for closeups, +26 steps for medium shot, +30 steps for full body. Face fix for 26+ steps. 1024x res with Euler a sampler. If you don't do it that way: With a lower resolution use highRes fix or enhance for the best quality possible.

Remove N-SFW negative prompts if you want to make N-SFW or background negatives if you want another simpler backgrounds.

My intention with this model was to create a fast model that worked great on higher resolutions (you still can use lower ones but it will be better with higher). V2 has a lot of improvements like better eye/face, hands, backgrounds... It will be a very experimental model. It seems to work very good with 1024x resolution and low steps. I made it merging some models I like. You can use lower steps if you increase resolution. Or you can also enhance the image. Not tested enough. v0 may have more issues but from v1 it should be fine enough with a good face, N-SFW and decent hands. v2 should have better backgrounds and eye/face, maybe hands too. This is just an experiment I'm making while I'm trying to improve my Everything-Mix model.

Issues: Sometimes bad anatomy. Increasing steps may fix it.

Komentarze