README.md

---
language:
- en
license: creativeml-openrail-m
thumbnail: "https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/showcase.jpg"
tags:
- stable-diffusion
- text-to-image
- image-to-image
---
# PoW : Somewhere

![Showcase](https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/showcase.jpg)

## Theme

You may have heard the expression “you are a product of your own environment.” What if that was quite literally the case?

Your “Something” grows closer to the mirror placed before you. You place your hand along the cold glass. You feel stuck. You feel like you’re waiting for… something to happen. Your mind feels like a mess, a bedroom you can never fully tidy up. You close your eyes, seeking solace in the silence. In the end, though… you still felt.

When you open your eyes, the small mirror from before has now covered every inch of the walls and floor.. Your attention draws to a new object that had appeared before you - a small, white keyboard. You examine it closely. Just a simple keyboard… but why was it here? You flip it over to see yet another small engraving:

“Take me Somewhere.”

Your heart raced with the intensity of a marching band playing a thunderous beat inside your chest.

Somewhere…? 

Continue your travels towards abstracted self-expression and self-discovery

* ”Somewhere” represents the environment of your own mind. If we weren’t humans– but could only be portrayed by landscapes, nature, and architecture.. What would we look like? What would that say about who we are?
* Maybe you’re moss filled ruins, or an amethyst ridden dungeon– an abandoned lighthouse on the beach, an overgrown garden. . .
* ”Somewhere” is your nature equivalent.

Won’t you take us Somewhere?

## 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 46 pictures. It was trained on [Stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) 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 .

## Trained tokens

* SDArt
* agne
* ohwx
* bnp
* atum
* aved
* bsf
* aten
* fcu
* cees
* chor
* cna
* nrf
* elio
* gani
* pfa
* kprc
* kuro
* asot
* elis
* bsp
* psst
* sqm
* irgc
* byes
* dany
* lpg
* miro
* avel
* vaw
* zaki
* guin
* pz
* reys
* crit
* doa
* suma
* taku
* ufos
* phol
* vedi
* dds
* weho
* pte
* oxi
* yuck
* zas

## Download links

[SafeTensors](https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/SDArt_somewhere.safetensors)

[CKPT](https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/SDArt_somewhere.ckpt)

[Dataset](https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/dataset.zip)

[Old version](https://huggingface.co/Guizmus/SDArt_somewhere/resolve/main/PoWStyle-Somewhere.safetensors)

## 🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).

You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().

```python
from diffusers import StableDiffusionPipeline
import torch

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

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

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