This lora was treined with some ????? uncut ?????, the images were generated using the model https://civitai.com/models/4201/realistic-vision-v13.
Its not much easy to get a ????? with this model, but its worth the try. My method is generating a bunch of small images, like 515x512 then when i get what i want i use the Hires. fix using the same seed with R-ESRGAN 4x+ and then you play with Denoising strength.
DDIM is the sampling method I use, it should work with DPM++ 2M Karras
Img2img and inpanting works aswell, any feedback is apreciated, thanks
You gonna see a lot of ??????? using this model
Im aware of the lacking of ???????, gonna work on that in the next versions
Like my models? Buy me a coffee!
Best used for inpanting, use the words, ???????, fuzzy ??????? or hairy ???????, this last one can make some "loose hole" lol
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
