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

Benutzer-LoRA

XL

Clonion Style [Pony XL]

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

  • App-Store
  • Google PlayStore
© 2026 PixAI
  • Nutzungsbedingungen
  • Datenschutzbestimmungen
  • Urheberrechtsrichtlinie
  • Gesetz über bestimmte kommerzielle Transaktionen
Clonion Style [Pony XL] - AI Model cover image
Hochgeladen am
17.04.2024, 06:17
Verwendet
906
Bewertungen
Keine Bewertungen
Berechtigungen
  • Bildgenerierung und -freigabe erlauben
  • Nutzern erlauben, dieses Modell herunterzuladen
  • Gewerbliche Nutzung

Empfohlene LoRAs

Hatsune Miku Aile d'Ange (Module) - AI Model cover image

Benutzer-LoRA

Hatsune Miku Aile d'Ange (Module)
9
Hatsune Miku Type 2020 - AI Model cover image

Benutzer-LoRA

Hatsune Miku Type 2020
5
Hatsune Miku Orbit (Module) - AI Model cover image

Benutzer-LoRA

Hatsune Miku Orbit (Module)
2
[Illustrious XL] Korone - AI Model cover image

Benutzer-LoRA

[Illustrious XL] Korone
1

Beschreibung

Makes high contrast colorful images similar in style to the artist Clonion.How to useThis LoRA performs best when background prompts are used, "simple background, "[color] background", "gradient background" and so on. A tip is to use a background color that contrast with one used for the character.A lot of the images in the dataset had text on them which wasn't feasible to remove without destroying large portions of the picture itself. Using other images wasn't an option either since the dataset was small to being with. As such you may see text on clothing and similar but using negative prompts or adjusting LoRA strength can lessen the risk of this.For further prompt tips please see the sample images and the uploaded zip of training tags.MISCTrained on Pony XL with a dataset of 37 images at 1024 resolution.All sample images are raw txt2img with no helper embeddings/negatives used. E.g. - things should look better if you do use them yourself.The training was done on a small subset of art, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the artist if you want the good stuff.

Kommentare