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

Electronic

Electronic-style generation. Covers: electronic music, synth pulses, driving beat, atmospheric pads, hypnotic energy; experimental electronic, glitchy textures, abstract rhythms, evolving sound design; and modern electronic dance track, layered synth leads, punchy drums, cinematic production.

Quick start

  • Base model: AceStep v1.5 Turbo (2B)
  • Trigger word: roti-3l3ktr0n (must appear in the prompt to activate)
  • Recommended strength: 1.0
  • Tested strength range: 0.3 โ€“ 1.5
  • Recommended steps: 8
  • Recommended guidance: 7.0
  • Recommended shift: 3.0
  • Sample rate: 48000 Hz

Example prompts

  • electronic music, synth pulses, driving beat, atmospheric pads, hypnotic energy (128 BPM, A minor)
  • experimental electronic, glitchy textures, abstract rhythms, evolving sound design (110 BPM, C minor)
  • modern electronic dance track, layered synth leads, punchy drums, cinematic production (130 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: 12 synthetic tracks, 2617s total, instrumental fraction 0.0

Files

  • electronic-v1.safetensors โ€” PEFT LoRA weights (88,130,248 bytes, sha256 2638e4906e5d5e2f6f6bc9aed87ddb00bef316eff4cf4942c144821332975792)
  • electronic-v1.metadata.json โ€” machine-readable sidecar (schema v1)
  • adapter_config.json โ€” PEFT adapter config

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

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