| ---
|
| license: other
|
| license_name: stability-ai-community
|
| license_link: https://huggingface.co/stabilityai/stable-audio-3-medium/blob/main/LICENSE.md
|
| base_model:
|
| - stabilityai/stable-audio-3-medium
|
| - stabilityai/stable-audio-3-small-music
|
| tags:
|
| - audio
|
| - text-to-audio
|
| - stable-audio
|
| library_name: stable-audio-3
|
| ---
|
|
|
| # SA3 Variations — fp16 weights
|
|
|
| Float16 conversions of Stability AI's [Stable Audio 3](https://huggingface.co/collections/stabilityai/stable-audio-3)
|
| checkpoints, repackaged for the Windows build of **SA3 Variations**.
|
|
|
| **These are Stability AI's models. This repo is a redistribution, not a new
|
| model, and is not affiliated with or endorsed by Stability AI.**
|
|
|
| ## Why this exists
|
|
|
| The SA3 Variations Windows app runs inference through PyTorch and needs its
|
| weights on disk at install time. The upstream repos are gated, which would mean
|
| every user creating a Hugging Face account and a token just to install a
|
| desktop app. This repo removes that step.
|
|
|
| ## What was changed
|
|
|
| Converted with [`scripts/convert_weights_fp16.py`](https://github.com/maxgraf96/stable-audio-3):
|
| every float32/float64 tensor cast to float16. Integer indices, masks and bools
|
| are untouched, and the bundled T5Gemma text encoder is left in **bfloat16** —
|
| bf16 to fp16 narrows exponent range and risks overflow.
|
|
|
| This is a storage change, not a quality one: the app loads with
|
| `model_half=True` on CUDA, so these weights were being cast to fp16 at load
|
| anyway. Verified by generating identical seeds from the original fp32 model and
|
| this conversion:
|
|
|
| corr(fp32, fp16) = +1.000000 (3 seeds)
|
|
|
| | | upstream fp32 | here |
|
| |---|---|---|
|
| | `medium/model.safetensors` | 9.22 GB | 4.3 GB |
|
| | `medium/t5gemma-b-b-ul2/` | 1.18 GB | unchanged (bf16) |
|
|
|
| ## Layout
|
|
|
| Each directory is self-contained — checkpoint, config, and its own copy of the
|
| text encoder, so the app can load it with a local path and no network access:
|
|
|
| ```
|
| medium/
|
| model_config.json
|
| model.safetensors
|
| t5gemma-b-b-ul2/
|
| small-music/
|
| model_config.json
|
| model.safetensors
|
| t5gemma-b-b-ul2/
|
| ```
|
|
|
| ## Licence
|
|
|
| Inherits the upstream terms, which you should read before using these files:
|
|
|
| - `medium/` — [stabilityai/stable-audio-3-medium](https://huggingface.co/stabilityai/stable-audio-3-medium)
|
| - `small-music/` — [stabilityai/stable-audio-3-small-music](https://huggingface.co/stabilityai/stable-audio-3-small-music)
|
|
|
| The bundled T5Gemma encoder additionally carries Google's
|
| [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|
|
|
| ## Source
|
|
|
| App and conversion script: <https://github.com/maxgraf96/stable-audio-3>
|
|
|
