LonaRPG Style.
I made this lora to try and reproduce the style of Lonarpg game. Now you can make your own art in the style of the game.
The above showcase images were made with Addetailer extension enabled and using a face and eyes model.
This LoRa is trained on Pony V6 and Illustrious 0.1, but I made the above showcase images in different checkpoints, because their style was more to my liking.
I added a new version trained on Illustrious 2.0, and with a bigger dataset. It should have better strength then the old 0.1 version.
Trigger: lonarpg,
Extra triggers: jaggy lines, pixelated, oekaki,
Advised strength: 0.6-0.9
Prompting Illustrious
For all versions I recommend you use: masterpiece, best quality, amazing quality, very aesthetic, high resolution, in your prompt and I myself am using the following negative prompt: text, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, lowres, (worst quality, bad quality:1.2), bad anatomy, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,
Prompting
For all versions I recommend you use: score_9, score_8_up, score_7_up, score_6_up, in your prompt and using the following negative prompt: score_5_up, score_4, score_3, score_2, score_1,
If you need a place to start take a look at the showcase images above.
Description
This version can somewhat reproduce Lona.
FAQ
Comments (4)
Love the style, but for some reason, it just doesn't work on faces. I tried it on my setup and on a clean install of Swarm, but almost no result. What could the problem be?
I myself don't work with Swarm. So can't help you there, but there could be some reasons the style doesn't stick. It could be other loras or the checkpoint itself. It could also be a module or a face fix setting that changes up the fave. So it is hard to pinpoint from just this comment.
@Ava_Choco my original setup is reForge. I tried it on clean Swarm. Tried on both without loras, different checkpoints. Tried with/without face adetailer, no results. Lora also seems very weak, i need to go 1.6/1.8 to get any results at all. Will try more checkpoints.
It could be because it was trained on Illustrious 0.1. But most lora from before march/april where trained on that checkpoint. My later lora should be on 2.0 at least if the Civitai trainer is on 2.0. But that is the only thing I can think of that might explain the lack of strength and even then I'm not sure, because it isn't consistent.