stable-diffusion text-to-image diffusers

Civilizations 6 Diffusion

This model was 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

Gradio

We support a Gradio Web UI to run Civilizations_6_Diffusion: Open In Spaces

Here are some samples.

Portraits c61.png c62.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

Disclaimers

License

Responsibilities

Thanks for checking out the model!