Views
No views yet
violin8s dataset (31 violin-performance clips).| 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) |
lora_weights_step_03000.safetensors — the LoRA adapter weights.