Folk
Folk-style generation. Covers: indie folk, fingerpicked acoustic guitar, soft male vocals, gentle harmonies; traditional folk track, acoustic guitar, fiddle, harmonica, warm vocals; and americana folk, fingerpicked guitar, lap steel, harmonica, heartfelt vocals.
Quick start
- Base model: AceStep v1.5 XL Turbo (5B)
- Trigger word:
roti-f0lkk (must appear in the prompt to activate)
- Recommended strength: 1.0
- Tested strength range: not evaluated
- Recommended steps: 8
- Recommended guidance: 7.0
- Recommended shift: 3.0
- Sample rate: 48000 Hz
Example prompts
indie folk, fingerpicked acoustic guitar, soft male vocals, gentle harmonies (95 BPM, G major)traditional folk track, acoustic guitar, fiddle, harmonica, warm vocals (110 BPM, D major)americana folk, fingerpicked guitar, lap steel, harmonica, heartfelt vocals (100 BPM, C 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, 3605s total, instrumental fraction 0.0
Files
folk-xl-v1.safetensors — PEFT LoRA weights (167,839,168 bytes, sha256 ce61fc9667723e2707bf06917ce6659ffdf70dd1bf80c9cabcf1458c59b99628)folk-xl-v1.metadata.json — machine-readable sidecar (schema v1)adapter_config.json — PEFT adapter config
Full metadata: see folk-xl-v1.metadata.json.
