I tried to remove the old yellow tint for V0.2, changed the captions a bit, and added some images to the dataset. The main drawback of V0.2 is that signatures appear more often at the bottom of the images.This checkpoint is a fine-tune from of the base SD XL model.The objective of this model is to reproduce traditional painting styles and artistic representations of classical themes.The trained artists are :EBls = Eugen von BlaasBnhr = Rosa Bonheurbchr = François BoucherWllBgr = William BouguereauCbnl = Alexandre CabanelCrvgg = CaravaggioChpln = Charles Chaplinedgs = Edgar DegasDLCRX = Eugène Delacroixdlflt = Albert EdelfeltDlpEjl = Delphin EnjolrasLRFlr = Luis Ricardo Falerofrnt = Émile Friantgrm = Jean-Léon Gérômegdwrd = John William Godwardltr = Henri Fantin-LatourEBLght = Edmund Blair LeightonAlfMch = Alphonse Mucharmnd = Raimundo de Madrazo y GarretaTdRll = Theodoros Rallirmbrndt = Rembrandt van RijnSrgnt = John Singer SargentSgnc = Guillaume Seignacsrll = Joaquín SorollaAZrn = Anders ZornSince I trained the model with a low learning rate, using the artist tag may not have a huge impact on the image. Employing them with their usual theme can work better.For resolution, you can use 768x1024, 768x1152, 896x1024, 1024x768, 1024x896, 1152x768.You can use it with my artist lora for XL to reinforce a specific style.I plan to update it later by training with a bigger dataset, curently it uses around 5000 images.
