Trained on similar dataset to version 4, on the Civitai trainer for Illustrious. Follow prompting instructions for Illustrious, using booru tags and "masterpiece, best quality" etc. along with "dcaustyle" and character prompts in description. I got pretty good results using it with the model WAI-NSFW-illustrious-SDXL, but you can try others.
Trained on similar dataset to version 4, on the Civitai trainer for Illustrious. Follow prompting instructions for Illustrious, using booru tags and "masterpiece, best quality" etc. along with "dcaustyle" and character prompts in description. I got pretty good results using it with the model WAI-NSFW-illustrious-SDXL, but you can try others.
324 images x 3 repeats x 16 epochs = 15,552 total
Optimizer: Prodigy
Clip skip 2
min SNR gamma=6
noise offset=0.05
alpha/dim=16/32