Type | |
Stats | 349 514 272 |
Reviews | (88) |
Published | May 29, 2025 |
Base Model | |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | rnsls2 |
Hash | AutoV2 F442B0C80C |
Changelog: 27/05/25
Alright, after playing with it for a bit, it feels like this LoRA works best when you're doing portraits and upper body images, this might be due to the dataset I used (which was limited), I'll look into it and maybe rework the dataset for a more flexible style.
Hi there, releasing this one as the first iteration of this LoRA, I'm still not quite sure as to how I'm feeling about it, I'll be testing more and maybe even rework the entire dataset once I feel like it, or get my buzz back anways, hope you guys enjoy it.
Recommended settings:
Strength 0.9, lower for more flexibility. Same goes for your cfg, anything below 4.0 is perfect or recommended. Also try not to use too many LoRAs together as it can deminish the quality of your image fairly quickly, or a high cfg will also do that.
I'd recommend using DPM++ 2M Karras for this one, as it feels more painterly, Euler A gives a more smoother painting style, up to you.
Thank you again for using my LoRA, you can support me through either donating Buzz, or you give a thumbs up, follow me or you can also use one of the links provided beneath my profile, anything helps really.