Dettagli
Raccomandazioni
v1.0
Toadstool

Toadstool

2
4
40
#Photorealistic
#concept
#mushroom
#model
#photorealism
#lora
#mushrooms

Foreword

In order to better understand the different types of models, I take the toadstool as the starting point for my investigation. At the moment I can create Embeddings, Hypernetworks as well as LoRAs. The generated results are satisfactory. Later on I will compare this LoRA model with a Hypernetwork and an Embedding. Therefore I will use the same database.

What the Model Does

The LoRA model transforms a mushroom into a realistic toadstool. This is where the characteristics of a mushroom come into play, such as a structured skirt and the scales on the caps. These details make the toadstool looks more natural.

Base Models which Works Well

In principle my LoRA model works with a bunch of base models. Some base models works better than other models.

Test case

One can use one simple test Prompt to check how good or how bad the model works.

Prompt without using the LoRA model:

mushroom

Prompt using the LoRA model:

mushroom, <lora:toadstool:1>

Trigger Words can be toadstool as well as mushroom or fungus.

Training

I trained the model with 50 photos of a toadstool. The resolution of all square photos are 1024 x 1024 pixel. The background of the used photos varies from sharp to bokeh. The environment in which the mushrooms grow also varies greatly. The stalk of the mushroom has a different length and thickness. The caps of individual toadstools are very different. They range from a flat cap to a spherical cap. Different viewing angles were used. The common feature in the photos is the reddish color of the cap.

Credits

For testing purposes I am using some models more often than others. My thanks go to the following models and their creators for there excellent work.

I am successively expanding the above list.

Finally

Have a nice day! Have fun! Be inspired!

Visualizza la traduzione

Valutazioni e recensioni

-- /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

Z
Conversazione con il modello
Annuncio
2024-09-13
Pubblicare modello
2024-09-14
Aggiorna le informazioni del modello
Dettagli modello
Tipo
LORA
Data di pubblicazione
2024-09-13
Modello Base
SD 1.5
Parola Chiave
toadstool
Copia
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