Three Versions the difference between is mainly dataset.
Ver 1: 50 photos US Department of Commerce and Labor, different people working nice high res and quality old photos.
Ver 2: previous 50 + 50 generated in style by Grok with focus on light and contrast.
Ver 3: previous 100 + 100 variety from panoramas to nudes and objects.
Check them all i really like to bump strength to 1.5 and gen in 2048 resolution, a more excessive prompt can help with the damaged look.
Description
I cant stop playing with the MMI it completely broken my training schedule i was working on this little app that cuts out the panels for the comic books then turns them into datasets :D :P but i lost my inspiration because of this model ;) , i did trained few more loras will publish them throughout the day after few tests dont really know if they worth anything. The 1900s lora is quite ok it makes viable improvement over the standard minimax capabilities or maybe I'm coping ;D. Civitai still don't have the proper home for MMI so im dumping them to "other" for now. Trigger: 1900s




