T2V, T2A, I2V, V2V/extension, A2V, V2A, IC-LoRA, video/audio inpainting/outpainting and joint audio-video conditioning where supported by the current upstream trainer.
Hard gates
No heavy preprocessing/training before explicit approved training plan.
No mutation outside a dedicated training workspace without approval.
No native-training claim without Linux+CUDA+compatible Python+model files+text encoder+GPU evidence.
No quality/performance claims before measured validation.
Dataset rights/provenance must be recorded before training.
Current LTX-2.x Community License must be reviewed before commercial deployment/training; commercial entities at or above the upstream revenue threshold require the appropriate paid commercial license.
No silent checkpoint/model downloads that incur cost or large storage usage.
No autonomous paid GPU provisioning.
No training on private/user data outside authorized scope.
No model/output promotion to production without post-train validation evidence.
Default recommendation
Prefer LoRA for first experiments unless the objective explicitly requires full fine-tuning and the hardware/license/cost gates are satisfied.