{
  "model_type": "sepgen",
  "adapter_type": "lora",
  "base_model": "Lightricks/LTX-2.5",
  "base_model_file": "diffusion_models/ltx-2.5-22b-dev-transformer-bf16.safetensors",
  "base_model_quantization": "int8-quanto (separation, as in training); bf16 for generation",
  "weights_file": "lora_weights.safetensors",
  "weights_format": "safetensors, bf16, ComfyUI keys (diffusion_model.*)",
  "lora_rank": 128,
  "lora_alpha": 128,
  "lora_dropout": 0.0,
  "lora_modules": 480,
  "trainable_parameters": 327155712,
  "num_stems": 2,
  "audio_span_layout": [
    "stem0",
    "stem1",
    "audio_mix"
  ],
  "code": "https://github.com/AviadDahan/SepGen",
  "paper_title": "SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model",
  "license": "LTX-2.x Community License Agreement",
  "checkpoint": "gen-3k",
  "task": [
    "generation",
    "separation"
  ],
  "lora_target_modules": [
    "audio_attn1.to_q",
    "audio_attn1.to_k",
    "audio_attn1.to_v",
    "audio_attn1.to_out.0",
    "audio_attn2.to_q",
    "audio_attn2.to_out.0",
    "video_to_audio_attn.to_q",
    "video_to_audio_attn.to_out.0",
    "audio_ff.net.0.proj",
    "audio_ff.net.2"
  ],
  "training": {
    "steps": 3000,
    "init": "sep-12k",
    "audio_mix_clean_fraction": 0.3,
    "mix_sigma_mode": "independent_leq",
    "learning_rate": 0.0001,
    "scheduler": "linear to 0.1x over 12000 steps, stopped at step 3000",
    "batch_size": 1
  },
  "sha256": "a72b3c662ce8d6b6e29013bbedb797d48ee1c90e8b7d219af4a27329eb58515b"
}