Dettagli
Raccomandazioni
v2.1pre-beta
v2.1pre-alpha
v2.0pre-alpha
v2.0pre-DPO
v1.6pre-beta
v1.6pre-alpha
v1.5pre
AlbedoBase XL Pre

AlbedoBase XL Pre

43.3K
146
1.0K
#อนิเมะ
#3D
#Photorealistic
#ศิลปะ
#all in one
#Base Model
#2D
#ภาพยนตร์
#Game
#unify

AlbedoBase XL Pre

The refiner is unnecessary, and VAE is included.


Please preview the next version of the AlbedoBase XL model and provide your feedback here. Once i gather and incorporate all the feedback, i will release the official version to the AlbedoBase XL side.


v2.1pre-beta

I revised the merging process and incorporated four checkpoints, originally designed for enhancement, throughout the system.

v2.1pre-alpha

I revised the merging process and incorporated four checkpoints, originally designed for enhancement, throughout the system.

The spec grid(424.4 MB): download

v2.0pre-alpha

The algorithm has been changed, and the DPO has been excluded. This is a test 2.0 version.

v2.0pre-DPO

- The Merge formula has been updated.

- The DPO model has been added.

- Full utilization of negative prompts is now available.

- Support for Clip Skip 2 has been introduced.

- Enhanced detail clarity for all samplers is achieved as the step count increases.

The spec grid(424.3 MB): download

v1.6pre

I've changed the algorithm of the Merge itself.

v1.5pre

I have written a custom script to converge the existing AlbedoBase XL models into one. Intricately aligning the row and column weights of all U-NET and CLIP blocks according to a unique equation, may produce a merging effect different from previous methods. It is still experimental, and I am so serious that I am immersed in the challenge of writing a paper independently (though I do not have a master's or doctorate in the field).

The spec grid(399.2 MB): download

I enjoy this work, and my curiosity and passion will not cease even if a better model comes out and AGI is developed.

Visualizza la traduzione

Valutazioni e recensioni

4.9 /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

avatar
Annuncio
2023-12-14
Pubblicare modello
2024-01-19
Aggiorna le informazioni del modello
Dettagli modello
Tipo
Checkpoint
Data di pubblicazione
2024-01-19
Modello Base
SDXL 1.0
Introduzione alla versione

I revised the merging process and incorporated four checkpoints, originally designed for enhancement, throughout the system.

Ambito di Licenza
Model Source: civitai

1. I diritti dei modelli ripubblicati appartengono ai creatori originali.

2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare

Ambito di Licenza di Creazione
Immagini Online
Effettua una Fusione
Consenti Download
Licenza Commerciale
Le immagini generate possono essere vendute o utilizzate per scopi commerciali
Consenti la rivendita del modello o la vendita dopo la fusione
QR Code
Scarica l'app SeaArt
Continua il tuo viaggio di creazione AI su mobile