If you want to show support, feel free to post, rate, follow, emote, or drop feedback! It helps!!! 😊🙇
Most images in dataset are from somewhat recent to capture a specific style... Many of their images feature Mashima’s characters colored directly from his manga panels.
No trigger word ... changes about this version
Illustrious Style v2
I used WAI-illustrious-SDXL v15 for these images, feel free to try other checkpoints! Trained on IIllustrious XL 1.0 which is what the current WAI v15 is partly based on. Certain checkpoint or LoRA(s) may heavily influence the style.
Generation details, prompts, and model info are listed with most images. CLIP IS always 2, displayed is bugged. CFG Scale 6 (5-7), 20-30 steps, and Euler a/DPM 2M as the sampler, Hires Remacri: Feel free to change!
Description
Overall quality boost with more flexibility
Better at following the prompt
Produces better results when combining multiple LoRAs
Trained on higher-quality images and the latest artist art style