Nagi Itsuki Style Lora | Noob/Pony - v1.0 [Pony]
Recommended Prompts
score_9, score_8_up, score_7_up, score_6_up, source_anime, <lora:Nagi_Itsuki_XL:1>, scenery
Recommended Negative Prompts
mosaic censoring, bar censor, censored, source_cartoon, source_pony, source_furry, simple background, blurry, blurry background, fading
Recommended Parameters
samplers
steps
cfg
clip skip
resolution
other models
Recommended Hires (High-Resolution) Parameters
denoising strength
Tips
Stick to close-up and simple concepts for best results.
Use fewer score tags for 'pony' to replicate simpler character styles like the artist's original.
Large scenery prompts may not work well due to SDXL limitations.
Creator Sponsors
Check out the Noob 1.0 V-Pred model used in version 2.0 training.
Learn about the AutismMix model used in version 1.0.
See these recommended SDXL settings to reproduce the showcased results.
This lora was trained on about 60 images from the artist Nagi Itsuki. The images used were mostly backgrounds with a few characters in between. The lora captures the style and shading but fails miserably to replicate the details of the source images backgrounds. You will notice this if you attempt to prompt a large scenery. I feel this is a limitation of SDXL more than anything.
I recommend you stick to close-up and simple concepts. The character style replication works well enough but it becomes influenced by the model once you begin to prompt concepts outside of the artist's territory. The actual character art of the source is much more simple than what you'll get from this lora due to the model. If you want something more simple similar to the artist's character style, I recommend using less score tags for pony.
Version 2.0 was trained on Noob 1.0 V-Pred.
Version 1.0 was trained on AutismMix and I haven't tested on anything else.
To get the results you see in the images above, these are the settings I used.
Contributor
Model Details
Discussion
Please log in to leave a comment.






