Severian-Void's picture
Update README.md
ca6299e
|
raw
history blame
2.17 kB
metadata
language:
  - en
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
license: creativeml-openrail-m

Starsector Portraits

This is a fine-tuned Stable Diffusion model trained on images from the videogame Starsector

Use the token starsectorportrait in your prompts for the effect.

Example prompts & tips

"a starsectorportrait of a person wearing a green balaclava and armored spacesuit"

"a starsectorportrait of an older man wearing a fancy suit with a purple cape"

Even with the training I found it was still useful to include some other phrases and tokens that can be helpful to more accurately match the base art style:

sabattier effect to get a more accurate lighting effect

brush strokes to achieve the more painterly feel of the portraits

conte if brush strokes is not doing enough or adding colorful artifacts to images this is another option

Sample images from the model:

output Samples output Samples

File Versions and Comparison Details

All version are trained using a hand labeled image set of 556 images with black/white backgrounds as well as flipped version of the same images

Any checkpoint version with pploss in the name were trained with prior preservation loss enabled and a regularization set of 8000 portrait images comprised of photos/paintings/digitalart of humans in modern day attire.

CFG and SAMPLE STEP comparisons between rc_v1 model files

(prompt: "a starsectorportrait of a person" sampler: euler_a) output Samples output Samples Adaptability comparisons between rc_v1 model files

(prompt: "a starsectorportrait of an alien cat" sampler: euler_a) output Samples