Details
Empfehlungen
v1.0
Looking down

Looking down

478
4
329
#Anime
#Konzept
#eyes

Hi!

This is an anime centered LORA that tries to make the characters look downwards.

Best use is with After Detailer or inpainting, as it has some strong color bleeding (as seen in the last example). It can be used regularly as well though.

For ADetailer I use a denoising strength of 0.3-0.5.

Also, using hires. fix always helps with faces in general. As there is more pixels for AI to work with.

Keywords are: lkn_down, looking away

Strength of: 0.8 - 1.2

Adding "(looking at viewer:1.3)" as a negative prompt helps a lot.

I usually add it just in the Adetailer negative prompt, but you can do it in both or just the main one.

The LORA isn't super accurate and might take some tries for it to work, but it's better than nothing I guess.

If you are interested in facial expression s control, I made this video (hope it helps): https://youtu.be/Lg2WeL5lVFY

Übersetzung anzeigen

Bewertungen & Kommentare

5.0 /5
0 Bewertungen

Noch nicht genügend Bewertungen oder Rezensionen erhalten

no-data
Keine Daten
avatar
N4Talent
16
1.4K
Chatte mit dem Modell
Mitteilung
2024-01-15
Modell veröffentlichen
2024-01-15
Modellinformationen aktualisieren
Modelldetails
Typ
LORA
Veröffentlichungsdatum
2024-01-15
Basismodelle
SD 1.5
Auslösewörter
lkn_down, looking away
Kopieren
Versionsvorstellung

Hi!
This is an anime centered LORA that tries to make the characters look downwards.

Best use is with After Detailer or inpainting, as it has some strong color bleeding (as seen in the last example). It can be used regularly as well though.

For ADetailer I use a denoising strength of 0.3-0.5.
Also, using hires. fix always helps with faces in general. As there is more pixels for AI to work with.

Keywords are: lkn_down, looking away
Strength of: 0.8 - 1.2

Adding "(looking at viewer:1.3)" as a negative prompt helps a lot.

I usually add it just in the Adetailer negative prompt, but you can do it in both or just the main one.

The LORA isn't super accurate and might take some tries for it to work, but it's better than nothing I guess.

If you are interested in facial expression s control, I made this video (hope it helps): https://youtu.be/Lg2WeL5lVFY

Umfang der Lizenz
Source-Modell: civitai

1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.

2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.

Umfang der Kreativlizenz
Online Generierung
Fusion durchführen
Download zulassen
Umfang der Business-Lizenz
Generierte Bilder können verkauft oder für kommerzielle Zwecke verwendet werden
Modelle können weiterverkauft oder nach der Fusion verkauft werden
QR Code
SeaArt App herunterladen
Setze deine KI-Kreativreise auf dem Mobilgerät fort