ltxv
#3
by
010O11
- opened
hello there! do you think it would be possible to make one unchained t5xxl for ltxv also? as tried this one in comfy, it gived me RuntimeError: Error(s) in loading state_dict for T5:
size mismatch for shared.weight: copying a param with shape torch.Size([69328, 4096]) from checkpoint, the shape in current model is torch.Size([32128, 4096]).
EDIT: good news! I learned to read !
010O11
changed discussion status to
closed