PixAI-Mitgliedschaft
PixAI
PixAI
Generate
Sign in
Startseite
Generation
Modelle
Studio
NEW
Wettbewerb
Mit Mio.2 erstellen
Toolbox
NEW
PixAI-Dokument

SDXL

Spooky

#Halloween

Erstellen

  • KI-Bildgenerator
  • KI-Animationsgenerator
  • Toolbox
  • Themengeneratoren
  • LoRA trainieren
  • Mio.2 Agent
  • Studio

Entdecken

  • Angesagte Tags
  • Rangliste
  • Modell-Marktplatz
  • Wettbewerb
  • Nachricht

Über uns

  • PixAI-Dokument
  • So verwendest du PixAI
  • Tsubaki.2
  • Mio kennenlernen
  • Inhaltsregeln

Preise & Hilfe

  • Mitgliedschaft
  • Credit-Pakete
  • Kontakt

Mobile App

  • Hol dir die PixAI-App
  • App-Store
  • Google PlayStore
© 2026 PixAI
  • Nutzungsbedingungen
  • Datenschutzbestimmungen
  • Urheberrechtsrichtlinie
  • Attributions
  • Gesetz über bestimmte kommerzielle Transaktionen
Spooky - AI Model cover image
Hochgeladen am
07.10.2024, 19:17
Verwendet
1.4k
Bewertungen
Keine Bewertungen
Berechtigungen
  • Bildgenerierung und -freigabe erlauben
  • Nutzern erlauben, dieses Modell herunterzuladen
  • Gewerbliche Nutzung

Beschreibung

Welcome!Spooky Season is upon us!  I put this together to build some spooky/scary/scarousing images for Halloween!  Using some of these tokens will help you get the most out of this merge:Spooky, dark atmosphere, horror, gothic, monster, Halloween If you haven't used my merges before, my focus has been creating models that I really like the style of "out of the box", without needing to tweak the visuals with tons of LoRA or TIs.  This model puts out some really nice looking 2d/2.5D images.  Please check out the resources linked in the Suggested section as well! All sample images were generated with no LoRA or TI.  I use Adetailer and Hires.fix on all of my gallery images.  Faces still generally look OK without Adetailer, but I recommend using it if possible.  I use face_yolov8s.pt for most of my uploads.  If you are new to Pony, here are some tips:Scoring - Use score_9, score_8_up, score_7_up, score_6_up, score_5_up in your positive prompt instead of SD1.5/SDXL quality tags.  I have personally found that my images have much lower chance of frying if I keep the tokens below 200 (I usually shoot for under 150 when possible). My base negative prompt looks like this: score_1, score_2, score_3, score_4, score_5, score_6, watermark, text, signature, logo, monochrome, muscular, censored, ugly Or use Zovya's Tis that do this for you with fewer keystrokes:https://civitai.com/models/332646/pony-pdxl-negative-embeddings You can also use some of the baked in sources and content ratings  to control  the kind of output you get: Sources - 'source_pony', 'source_furry', 'source_cartoon' and 'source_anime'Ratings - 'rating_safe', 'rating_questionable' and 'rating_explicit'  My Usual Settings / Other Tested OptionsSampler -DPM++ 2M SDE Karras / Restart / Euler ASteps - 30--50 (30 for fast gens to test ideas, 50 for things I may save/post)Resolution -896x1152, 832x1216 (or flip for landscape) Hires.fix:Upscaler - Ultramix_balanced, 4x_UltrasharpSteps - 15 or 20Denoise -.3-.4Upscale by - 1.5 - 2.0

Kommentare