Originally, I did it more to create cyber architectures and characters to my own taste. In the end, it produces harsher lights, lowers the color saturation and the lines are more pronounced, for a sort of manhwa style. You can use settings higer than 1 to be more pronounced.
The final rendering is biased, BUT there are some talented people around here, so don't hesitate to SHOW ME WHAT THIS LoRa IS CAPABLE OF!
This is the simpliest way to help me to improve the quality of a possible future model training and donate some BUZZ to train new ones on PonyXL or Flux with Civitai later.
I would be very grateful if you could donate some Tips to help me if you can. Officially, it would allow me to improve my GPU which is not powerful enough to training locally at the moment. Honestly I know I will never receive enough for this, but it will already be perceived as a very much appreciated comfort and encouragement from you.
Thanks for your interest, and have fun!
Picture by CzernobogDescription
Don't forget to specify "monochrome" for example in the negative prompt if you want to keep color in the final rendering and you will have a good chance of seeing a humanoid figure appear in your image if you only wanted a landscape.
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.