SDArt : Encapsulated (version based on 2.1 768px)

Theme

What if the world was in the palm of your hands? Condensed, contained, and captured within a simple sphere for all to see?

Create your own world encapsulated within an orb, sphere, container etc. This can be any type of world or landscape you can imagine, but it must be confined within the boundaries of the orb.
Bring your miniature world to life. Big things come in small packages!
A world made of crystals and moss? A lush forest landscape? An upside-down world? A world made of instruments? A world made of tangled wires? Be creative! Be uniquely you!

Model description

This is a model related to the "Picture of the Week" contest on Stable Diffusion discord.

I try to make a model out of all the submission for people to continue enjoy the theme after the even, and see a little of their designs in other people's creations. The token stays "SDArt" and I balance the learning on the low side, so that it doesn't just replicate creations.

The total dataset is made of 36 pictures. It was trained on Stable diffusion 2.1 768px. I used EveryDream to do the training, 100 total repeat per picture. The pictures were tagged using the token "SDArt", and an arbitrary token I choose. The dataset is provided below, as well as a list of usernames and their corresponding token.

The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .

The model is also available here in a version trained on 1.5 as a base.

Trained tokens

SDArt
bnp
aten
fcu
cous
aved
arum
omd
kuro
asot
psst
buon
utm
vaw
mss
guin
mgt
crit
isch
phol
vedi
dds
acu
pte
oxi
rean
reba
reem
revs
rith
rmb
rolf
ront
rps
rsc
gare
shld

Download links

SafeTensors

Config (yaml)

Dataset

🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.

You can also export the model to ONNX, MPS and/or FLAX/JAX.

from diffusers import StableDiffusionPipeline
import torch

model_id = "Guizmus/SDArt_Encapsulated768"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "SDArt kuro"
image = pipe(prompt).images[0]

image.save("./SDArt.png")