The style of Domi.

I made this lora to try and reproduce the style of Domi (hongsung0819).

Illustrious V2

I remade this version, because it was made based on pony lora creation settings. Because of this some things have changed.

For the quality tags I used the following: masterpiece, best quality, blurry, bloom (I added blurry and bloom to try to capture the effect of the original art, so they are not mandatory)

For the negatives I used the following in general: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,

I used ADetailer plugin with the a face model to improve the quality, but this is not mandatory to get good results..

The Trigger is: domi-h2o,

Advised strength: 0.6-1.0

Illustrious V1

So for this version I recommend you use: masterpiece, best quality, elegantly detailed, in your prompt and I myself am using the following negative prompt: text, long body, lowres, cropped, lowres, (worst quality, bad quality:1.2), jpeg artifacts, signature, watermark, username, signature, simple background, conjoined, out of frame,

The above showcase images were made with Addetailer extension enabled and using a face and eyes model.

This LoRa is trained on Illustrious 0.1, but I made the above showcase images in different checkpoints, because their style was more to my liking.

The Trigger is: domi-h2o,

Advised strength: 0.6-0.9