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

Progressive Rock

Progressive Rock-style generation. Covers: progressive rock, complex song structure, soaring guitar solo, organ, dynamic; epic prog rock anthem, time signature changes, virtuosic instrumentals; and mellow progressive rock, intricate arpeggios, atmospheric synths, lyrical guitars.

Quick start

  • Base model: AceStep v1.5 Turbo (2B)
  • Trigger word: roti-prgr0k (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

  • progressive rock, complex song structure, soaring guitar solo, organ, dynamic (110 BPM, D minor)
  • epic prog rock anthem, time signature changes, virtuosic instrumentals (130 BPM, E minor)
  • mellow progressive rock, intricate arpeggios, atmospheric synths, lyrical guitars (90 BPM, F# major)

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, 4812s total, instrumental fraction 0.067

Files

  • progressive_rock-v1.safetensors โ€” PEFT LoRA weights (88,130,248 bytes, sha256 637d19149a34e9094e91987b6df3190b4d93d6bfbb25c0507e14633bc2d0ecba)
  • progressive_rock-v1.metadata.json โ€” machine-readable sidecar (schema v1)
  • adapter_config.json โ€” PEFT adapter config

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

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