Are you planning to make gemma-3-27b-it-abliterated compatible with LTX-2 anytime soon?
#2
by
aomsan461
- opened
👇
Sure I'll have to try it out first though. My hunch is given that LTX2 was trained on the 12b model, the 27b may have embeddings the DiT doesn't understand and will generate strange results. But hey, one way to find out. Maybe a week or so before I have good internet again to see how it goes.