Downloads · 30 days
0
HaileyStorm/sv-billie-yue2-lora
sv-billie-yue2-lora is a text-to-audio model from HaileyStorm. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
A YuE2-3B adapter for close, hushed vocals, heavy low end and off-kilter bedroom pop... sounds... familiar...
Downloads · 30 days
0
Access
Public
Updated Sep 21, 2026
Repo size
1.2 GB
Likes
4
Public
Click a slice to open those files.
.wav710 MB · 59%
From the Hugging Face model README
A YuE2-3B adapter for close, hushed vocals, heavy low end and off-kilter bedroom pop... sounds... familiar...
Selected checkpoint: step 950. Rank-32 PEFT-format adapter trained with AI Toolkit on an artist-focused recorded-music corpus. Training audio is not redistributed. This repository contains the adapter, not the base model or VAE.
Eight original generated songs. 3 seeds x 3 sampler configs, best generation picked (some songs all generations discarded)- no edits or other manual work. Except for Porch Light, which was one generation per LoRA checkpoint.
For best demonstration of LoRA result, start with Smile for the Meter, then The Fridge Light and No Applause in the Kitchen. Album files: MP3, FLAC, WAV, lyrics and style prompts.
<img src="examples/the-long-way-back/cover.png" width="360" alt="sv-billie — The Long Way Back cover">01. Smile for the Meter · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/01%20-%20Smile%20for%20the%20Meter.mp3"></audio>
02. Velvet on the Handbrake · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/02%20-%20Velvet%20on%20the%20Handbrake.mp3"></audio>
03. The Seat Beside You · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/03%20-%20The%20Seat%20Beside%20You.mp3"></audio>
04. Spare Key · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/04%20-%20Spare%20Key.mp3"></audio>
05. Porch Light · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/05%20-%20Porch%20Light.mp3"></audio>
06. The Fridge Light · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/06%20-%20The%20Fridge%20Light.mp3"></audio>
07. No Applause in the Kitchen · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/07%20-%20No%20Applause%20in%20the%20Kitchen.mp3"></audio>
08. Last Ferry, First Bird · MP3
<audio controls preload="none" src="https://huggingface.co/HaileyStorm/sv-billie-yue2-lora/resolve/main/examples/the-long-way-back/08%20-%20Last%20Ferry%2C%20First%20Bird.mp3"></audio>
Porch Light is an earlier step-900 example. Last Ferry, First Bird uses step 950 plus a DreamPop adapter at 0.3, which is not included here. Other album tracks use this artist adapter alone. Some endings await manual trimming. Exact selected settings and seeds are in the album manifest. These are curated examples, not a guarantee of consistent quality or lyric adherence.
This adapter is free and donations are entirely optional. Donations help sustain Hailey's hands-on AI work: past chess and Mamba-model work, and current or future work around Maestro Continuum, Palimpsest, Loom/ScaFOLD, an experimental Qwen3.8-27B abliteration/efficient-reasoning model, other tools, and whatever comes next. Donations never privilege or discourage any model, provider, or host route, and no available donation method below is preferred:
1K628QLEh3sS8sEdzZfvuqqHRecVckSgaJaddr1q9fd05jktgv49094z8hvjp6cqvn7npt8hfzjna4dvhezmvpgl92x5cevqghl4ng0we2es4xjp59gvm3nttdzwf9ym6lqr3628x0x78b6adac22415568A7F725a865206ccFd1a82F4c[email protected]. Vast.ai says transfers are irreversible, so double-check the recipient before confirming.See the donation instructions for QR codes, Vast.ai instructions, and safety notes.
Load sv_billie.safetensors with a YuE2-compatible LoRA loader (AR + NAR),
starting at strength 1.0. Use YuE2-3B
and YuE2-Vae. The included lora.json
provides the display name and trigger for Sound and Vision.
Prepend sv_billie, in the style of sv_billie. to your style caption, then
specify genre, instruments, language and tempo. Supply full section-tagged
lyrics. Album ABC plans and lyric files are separate; supplied ABC bypasses
score planning.
| Profile | AR temperature | top-p | top-k | repetition penalty |
|---|---|---|---|---|
| Default | 0.88 | 0.96 | 115 | 1.20 |
| Focused | 0.82 | 0.94 | 100 | 1.24 |
| Exploratory | 0.94 | 0.975 | 130 | 1.18 |
Use 100 ODE steps, CFG 1; score sampling 0.8 / 0.925 / 40 when planning. These are general starting profiles; album takes used individual variants. Choose generous duration headroom. Random seeds are recommended for exploration; 2029 is a convenient fixed seed, not a proven quality improvement.
See https://huggingface.co/Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4.
Adapter: CC BY-NC 4.0, following the non-commercial base-model license. Credit the YuE2 team and this adapter repository. The base license does not grant rights to third-party recordings, identities or likenesses. Samples are AI-generated demonstrations with newly written lyrics; no source recordings are included.