Pixel Art Diffusion

Trained on an original dataset of 4,000+ pixel art landscapes and portraits by Kali Yuga

  • Description

    Pixel Art Diffusion is a custom-trained unconditional diffusion model trained on an original (small) dataset of 4,000+ 256x256 pixel art landscapes and portraits by Kali Yuga using the fine-tuning openai diffusion model notebook.

    The result is a generative model that can create new, high-resolution images of pixel art landscapes and portraits with a variety of styles.

    The main benefit of this technique is that it can produce images with a wide range of styles, from traditional to abstract, without the need for specific training data for each style.

    This makes it ideal for creating new art with a variety of styles, or for creating variations on existing art. In addition, the Pixel Art Diffusion technique can be easily applied to other types of images, such as photographs, to create new effects.

  • Batch size

    This model creates 1 image per credit

Pixel Art Diffusion

Examples

Browse images created using Pixel Art Diffusion

dark prison cell made of cobblestones with vines on the walls
magical fantasy ruins in a forest
man walking through enchanted forest

Try this model for free

Signup today to use on this and any of the other models Accomplice has to offer

Start creating