Detail
Rekomendasi
v3.0
v3.0plus
v2.0
v1.0
MHXL - Aventis Horizon (SDXL)

MHXL - Aventis Horizon (SDXL)

494
14
2
#Anime
#abstract
#Surrealism
#realism
#Base Model
#Bentuk manusia
#artistic
#Cartoon
#Fantasi
#General
#best
#sfw
#creative
#stylistic
#SDXL
#sdxl 1.0

Read more about the technical capabilities of Aventis Horizon, https://civitai.com/articles/4828

Notice: I absolutely adore Aventis Horizon v3 and how it works, it has it's own particular quirks as any model does, but very little that I'd care to modify and change. I have several unreleased versions and I'm just not happy with the changes. My new model Penrose Augment is a spiritual successor and the closest thing to a v4 that I've been happy with, so if you like Aventis, please go try Penrose Augment!
V3 BAKED VAE: SDXL FP16 VAE Fix
V3-Plus BAKED VAE: SharpSpectrumVAE by Pitpe11 - Don't have it? Get it here!

Introducing Aventis Horizon, a general purpose model built using bleeding edge techniques for mixing prompt adherence with artistic and stylistic flair, improving emotional expression, improving artistic comprehension, and mixed media generation. Using custom trained for purpose models in combination with royalty free community resources for an artistic twist.

For best results:
CFG: 1.5-7 (4.5) || Steps: 16-250+ (20-60)

Make use of stylistic descriptors, style types, and mixed styles prompting. If you have trouble with basic generations coming out oversaturated try adding the following styles to your negative: 8bit, pixel, cartoon, anime, unrealistic.

Lihat terjemahan

Rating dan Ulasan

-- /5
0 rating

Belum menerima penilaian atau komentar yang cukup

avatar
Pengumuman
2024-03-03
Memposting model
2024-07-01
Perbarui informasi model
Detail model
Jenis
Checkpoint
Waktu publikasi
2024-04-22
Model Dasar
SDXL 1.0
Perkenalan versi

Refined style capabilities for anime, cinematic, intricate patterns, tattoos, and more.

Further improvements to prompt coherence and creative interpretation.

Improved general coherence further reducing min cfg to 1.0 without needing lcm or turbo.

Allows for improved animatediffXL and HotshotXL outputs with faster processing.

Cakupan Lisensi
Model Source: civitai

1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.

2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim

Cakupan Lisensi Penciptaan
Gambar Online
Melakukan Penggabungan
Izinkan Unduhan
Lisensi Komersial
Gambar yang dihasilkan dapat dijual atau digunakan untuk tujuan komersial
Izinkan model dijual kembali atau dijual setelah penggabungan
QR Code
Unduh SeaArt App
Lanjutkan perjalanan kreasi AI Anda di perangkat mobile