Feel free to post, rate, follow, or drop feedback! 😊🙇
Training mainly focuses on Mikozin's latest art/style. For v3 all characters in the training data were properly tagged. Changes listed in About this version.
I used WAI-illustrious-SDXL v14 for these images, Hassaku XL1.3 Style A also works quite well. Feel free to try other checkpoints! Though certain checkpoint or LoRA(s) may heavily influence the style.
Generation details, prompts, and model info are listed with each image. CFG Scale 5 (4-6), 30 steps, and Euler a as the sampler. Feel free to change.
Use Trigger Word: mikzn
Description
Removed older and stylistic inconsistent images
Added new images from the artist
Ensured all characters in the training data were properly tagged (with a few exceptions for OCs)
Reviewed and updated images to include halos, correct eye color prompts, etc
Trained on Illustrious, since I never really use Noob... Settled after a lot of buzz and trial 😭 maybe someday if I ever get a new GPU for local training.
Focuses on latest artwork style (2023-2025)
Remember to use trigger word not artist name.
A lot softer, not as rough compared to before. More aligned with artist style.
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.