Skip to content

grexzen/SD-Chad

 
 

Repository files navigation

SD Chad - Stable Diffusion Aesthetic Scorer

Have been using SD to create art for the last month, finding a template that works across prompt, seed, settings, and then creating 100s of images from it, selecting the best, deleting the rest.

That flow works great already, have lots of pics that look as good as those trending on ArtStation. Then I thought about automating this using AI. Here is what I have done so far:

Now I am retraining the scoring model again using the top 2,500 images scored from 200K gens (1.5 model + new VAE + style = best gens so far), and handpicking the few images that I would personally published in my art channels. First test was great, the model really seems to understand which images I would pick.

SD Chad Script

image

ASV1 vs ASV2

Here is ASV1. Album score =10 https://ibb.co/album/cY7GQW. Album score = 0 https://ibb.co/album/84p0Bk.

image

Here is ASV2. Album score = 8 (highest) https://ibb.co/album/ypWyhL. Album score = 2 (lowest) https://ibb.co/album/0Rk3Yx.

image

ASV1 has a nicer distribution of scores, while ASV2 is pretty tight in the middle. Since ASV2 was created by scoring non-gens that might be why is so strict scoring gens from SD. It also seems to prefer realistic images.

image

ASV2 vs CSV1

ASV2 is great for scoring your images vs other gens + no gens (SD vs real pics) and CSV1 is great for scoring your images vs other gens only (SD vs SD).

Below are the distributions, average scores, and 2 & 3 standard deviations from the mean.

image

About

SD Aesthetic Gens Algo

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%