Train Model

End-to-end agent for training LTX models. Probes filesystem and GPU, picks the right conditioning mode from the user's intent, prepares the dataset (scenes, captions, references), preprocesses, autotunes, launches, and monitors training. Use when the user wants to train, fine-tune, LoRA, or otherwise produce a custom LTX model.

lightricks Updated

File contents

lightricks/ltx-2 commit a20239e88a

Frequently asked questions

npx get-skill add lightricks/train-model