README.md

---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
- diffusers
inference: true
---

### Civilizations 6 Diffusion
This model is trained on the leaders portraits/loading screens, and the splash arts.
However, it was not trained on the gameplay map at all.

To reference the art style, use the token: civsix style

Here are some samples.

**Portraits**
![c61.png](https://s3.amazonaws.com/moonup/production/uploads/1670351131093-635eafb49f24f6db0a1eafd1.png)
![c62.png](https://s3.amazonaws.com/moonup/production/uploads/1670351131104-635eafb49f24f6db0a1eafd1.png)

Prompt used:
Portrait of *name* in civsix style, 8k
Negative: blurry
Guidance: 8
Steps:  50-75 using DDIM

I'm not a prompt wizard so you can definitely get better results with some tuning.

**Objects**
![c63.png](https://s3.amazonaws.com/moonup/production/uploads/1670351130886-635eafb49f24f6db0a1eafd1.png)