LTX-2 violin8s LoRA (rank 64)

LoRA adapter for the Lightricks LTX-2.3 22B audio-video model, fine-tuned on the violin8s dataset (31 violin-performance clips).

This is the exact checkpoint used to generate the v3/v4 with-LoRA side-by-side comparison clips.

Training

Base model ltx-2.3-22b-dev
Method LoRA (rank 64, alpha 64)
Target modules to_k, to_q, to_v, to_out.0
Learning rate 5e-4
Step 3000
Effective batch 8 (4×DDP × grad_accum 2)
Precision bf16
Mode video-only (audio disabled)

Files

  • lora_weights_step_03000.safetensors — the LoRA adapter weights.

Access

This repo is gated with manual approval — request access and the owner will review it.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support