Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string

Industrial

Industrial-style generation. Covers: industrial track, mechanical percussion, distorted synths, harsh metallic textures; industrial rock, distorted guitars, drum machine groove, screamed vocals; and industrial dance, pounding kick, distorted vocals, gritty synth bass.

Quick start

  • Base model: AceStep v1.5 Turbo (2B)
  • Trigger word: roti-1ndstrl (must appear in the prompt to activate)
  • Recommended strength: 1.0
  • Tested strength range: 0.3 โ€“ 1.0
  • Recommended steps: 8
  • Recommended guidance: 7.0
  • Recommended shift: 3.0
  • Sample rate: 48000 Hz

Example prompts

  • industrial track, mechanical percussion, distorted synths, harsh metallic textures (120 BPM, D minor)
  • industrial rock, distorted guitars, drum machine groove, screamed vocals (130 BPM, E minor)
  • industrial dance, pounding kick, distorted vocals, gritty synth bass (135 BPM, F minor)

Training

  • Rank 64, alpha 128, dropout 0.1
  • Target modules: q_proj, k_proj, v_proj, o_proj
  • 500 epochs / 7500 steps, batch 1, optimizer adamw_fused, lr 0.0003, warmup 100
  • Dataset: 15 synthetic tracks, 3886s total, instrumental fraction 0.267

Files

  • industrial-v1.safetensors โ€” PEFT LoRA weights (88,130,248 bytes, sha256 c36880148a7e370140a7333e31797a5721e51770c2121381bff398f925607117)
  • industrial-v1.metadata.json โ€” machine-readable sidecar (schema v1)
  • adapter_config.json โ€” PEFT adapter config

Full metadata: see industrial-v1.metadata.json.

Downloads last month
11
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support