Dettagli
Raccomandazioni
v1.0
Game icon (also: , , kittens)

Game icon (also: , , kittens)

752
10
147
#objects
#card
#Game
#icon
#เกมกระดาน

So I was doing on my PC, when suddenly ...

I tried to fit a LECO with PartiPrompts, with added words ', , kittens' to every prompt. This means that the model has to find a Lora that transforms the image of 'a power drill' into something that would be the result of the prompt 'power drill, , , kittens' and 'Van Gogh's starry night' into 'Van Gogh's starry night, , , kittens', etc.... Since there are no words in the prompt to support those additional elements, the model should hilariously collapse (you're trying to draw something that is not in the prompt, so the prompt is useless, so the prompt to image model collapses).

Very surprisingly, it produced something useful, so I posted it.

With negative weight, the model becomes very literal, making it useful for drawing equipment icons for games (video games or board games).

With negative weight:

  • the model becomes literal, and draws only what is in the prompt

  • the colors are less intense (might need to use the image as a scribble/lineart controlnet)

  • perspective is simpler (even isometric or flat)

  • there are less outside elements (background, walls, characters, hand holding the object)

  • the object is sometimes slightly out of frame (might need to outpaint or try 'out of frame' in the negative prompt)

With positive value:

  • will produce a lot of organic looking garbage optical illusion (I like it, it reminds me of Otomo Katsuhiro, but without the sense of composition)

Training files are not included (just take the training files from 'another aesthetic slider' and replace 'masterpiece, best quality' with ', , kittens').

Visualizza la traduzione

Valutazioni e recensioni

5.0 /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

no-data
Nessun dato disponibile
R
Conversazione con il modello
Annuncio
2024-01-08
Pubblicare modello
2024-01-08
Aggiorna le informazioni del modello
Dettagli modello
Tipo
LORA
Data di pubblicazione
2024-01-08
Modello Base
SD 1.5
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