---
language:
- en
license: creativeml-openrail-m
thumbnail: "https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/showcase.jpg"
tags:
- stable-diffusion
- text-to-image
- image-to-image
---
# SDArt : Synesthesia (version based on 2.1 768px)

![Showcase](https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/showcase.jpg)

## Theme

Dear @Challengers ,

> In a world where colors have flavor, and sounds have texture, 
> The senses intertwine to create a sensory rapture.
> Welcome to “Synesthesia”- where the ordinary is extraordinary,
> And art takes on a meaning that’s truly visionary! :Rainbowpink: 

Synesthesia /ˌsɪn.əsˈθiː.ʒə/: an anomalous blending of the senses in which the stimulation of one modality simultaneously produces sensation in a different modality. Synesthetes hear colors, feel sounds, and taste shapes.

* Create an image that captures the essence of synesthesia sensory! Explore the intersections of sound, color, and texture. What’s it like tasting a melody, feeling a scent, or seeing colored words?

* What would it look it look like to taste the sound of a thunderstorm? How would you visualize the sensation of feeling the warmth of the sun on your skin? Or how about tasting a particular color–such as a bright red apple or a cool blueberry?

* Explore the possibilities of synesthesia and its many interpretations!


## 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 39 pictures. It was trained on [Stable diffusion 2.1 768px](https://huggingface.co./stabilityai/stable-diffusion-2-1). 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 .

[The model is also available here](https://huggingface.co./Guizmus/SDArt_synesthesia) in a version trained on 1.5 as a base.

## Trained tokens

* SDArt
* dyce
* bnp
* keel
* aten
* fcu
* lpg
* mth
* elio
* gani
* pfa
* kprc
* cpec
* kuro
* asot
* psst
* sqm
* irgc
* cq
* utm
* guin
* crit
* mlas
* isch
* vedi
* dds
* acu
* oxi
* kohl
* maar
* mako
* mds
* mert
* mgt
* miki
* minh
* mohd
* mss
* muc
* mwf

## Download links

[SafeTensors](https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/SDArt_synesthesia768.safetensors)

[CKPT](https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/SDArt_synesthesia768.ckpt)

[Config (yaml)](https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/SDArt_synesthesia768.yaml)

[Dataset](https://huggingface.co./Guizmus/SDArt_synesthesia768/resolve/main/dataset.zip)

## 🧨 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_synesthesia768"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

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

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