i can't really make sense why some models work and some models just will not work at all.
5
#5 opened about 1 month ago
by
kellempxt
Is this only the ContrastiveLoss finetuning? Did you use the Coarse-grained alignment loss proposed in LongClip?
1
#4 opened about 2 months ago
by
cuifeng
"Finally working: Redundant TEXT model for HF inference". Could you do the same thing for this LongClip?
7
#3 opened 3 months ago
by
kk3dmax
AssertionError: You do not have CLIP state dict!
5
#2 opened 4 months ago
by
PixelClassisist
SDXL usage
4
#1 opened 4 months ago
by
apiasecki