Dettagli
Raccomandazioni
V1
MesoAmerican-Codex-V2

MesoAmerican-Codex-V2

11
6
59
#ประวัติศาสตร์
#Style
#symbolism
#codex
#illustration style
#meso-american
#FLUX

This is V2 with better training parameters. I think it came out well. I'm going to hide the 1st version.

If anyone has knowledge about the meaning of the glyphs please DM me! I'd love to learn more about these.

I've been fascinated with the art of old manuscripts. The Mesoamerican codec are truly incredible artworks but had also real purpose. They were painted onto dried deerskin strips and folded up into books. I've been trying to learn what all the different day signs and glyphs mean in order to best interpret the panels.

It will have an effect without tags, however you will get more by adding Glyph or Codex. Panel, multipanel will also help but will make the image flatter - and have panels divided by red lines. I tried to train the model with the names of the different day signs and gods, so those will work well too.

Examples:

  • Water god or Atl

  • Death God or Miquiztli

See the table below for more suggestions

It seems like this Lora works well in combination with other Lora and also with many different Flux base models, but it was trained with the BFL Dev1 flux. If you experiment with it and get something cool, please share!

Many of the images I used came from the Bodleian Library, Oxford University which I thank. They have a CC-BY-NC-4.0 license which means they are free to be shared and adapted, but not used commercially. I have extensively edited most of the training images in Photoshop to clean them up and make them less age affected.

Here's a little chart I made with the different day signs and glyphs. It might be helpful for making prompts and things.

Visualizza la traduzione

Valutazioni e recensioni

-- /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

no-data
Nessun dato disponibile
Conversazione con il modello
Annuncio
2024-10-30
Pubblicare modello
2024-10-30
Aggiorna le informazioni del modello
Dettagli modello
Tipo
LORA
Data di pubblicazione
2024-10-30
Modello Base
Flux.1 D
Introduzione alla versione

better training - used prodigy, 1e-5 learning rate, DIM 32

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