LORA Trainable?
#5
by BallisticAI - opened
Are we able to train a LORA from samples using your model? Do you have any advice on how do to that?
BallisticAI changed discussion title from Trainable? to LORA Trainable?
We haven't released training code yet, but LoRA fine-tuning on this architecture is definitely possible. Resemble AI's DramaBox project does exactly this on the same LTX 2.3 audio base with
IC-LoRA, so there's a reference implementation out there if you want to get started now.
The key things to keep in mind: target the self-attention layers (not cross-attention, you want to preserve prompt adherence), and use rank 128. If you're training for a specific voice identity,
include 10-20 seconds of reference audio in ~30% of your training samples.