Howdy, after countless tests and failed attempts, this is the only version that consistently gave me good results, so I'll be dropping this version as an experimental version and maybe rework on the dataset once again, I think my failed attempt is on tagging, so I'll be giving it another try later... so anyways, hope you guys enjoy it. This is trained on 3DCG images & some GTA VI's screenshots, hence why it is a mix, it definitely has that GTA vibe and quality sometimes, but not always, give it a go and see how it fairs.
Recommended settings:
Strength 0.9, lower for more flexibility. Same goes for your cfg, anything below 4.5 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.
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.
