with matching what do you mean? the images you used for training were only faces?
with matching what do you mean? the images you used for training were only faces?
Flol
Chahah
Fi mean generating an image that has my face and riding a dinasaour
Cnot baad, but too much cgi, 3d, 90s style
Cand... it is you at 80%?
F
Fvery similar this one
Cyeah
Flol
Cwtf
Cxd
Falmost there haah
Ctry more steps with same seed
Fdecent one
Cthat one was cool
Cso the closer the better accuracy
Clike always
Csd 2.1. TI
Cso TI works in sd 2.1
F
Fyes ti sd 2.1
Fnow will test step count on this
Ctoo much like a videogame of 1995
Fdo you know format for that
Ctry negative prompts like CGI or 3D
Fok 1-50 worked
CI find Euler makes it
Chrfhfhrf
Cand DPM2 a Karras for some strange reason makes it more accuracy
C*accurated
Flooks like dinasaur underlying knowladge is from cheap cgi movies
Chehehe
Fi will try Jurassic park
Cmaybe the nerfed 2.1. version
Clacks copyrighted images
Cwhy dont you try another cooler 2.1 model? the same TI .pt file will work
Fwhich one there are good
Flooks like most of them are on 768
Cyep
Cmaybe the 512 you trained works on 768
Cas long as it is in sd 2.1
F
Fi think they have to be exactly same for best
Csame?
Fsame model
Fwhere ti is trained
CI think so
Ctried today with protogen to train and it worked better
Canyway it can make it; I have been using a trained model 1.5 for a lot of models and worked somehow
Fmajority of models based on 1.5