Delete LatentSync-1.6-GGUF
Browse files
LatentSync-1.6-GGUF/README.md
DELETED
|
@@ -1,47 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: mixed-upstream-licenses
|
| 4 |
-
license_link: https://github.com/deepinsight/insightface#license
|
| 5 |
-
tags:
|
| 6 |
-
- audio.cpp
|
| 7 |
-
- gguf
|
| 8 |
-
- lip-sync
|
| 9 |
-
base_model: ByteDance/LatentSync-1.6
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
-
# LatentSync 1.6 for audio.cpp
|
| 13 |
-
|
| 14 |
-
Use this package with [audio.cpp](https://github.com/0xShug0/audio.cpp).
|
| 15 |
-
It synchronizes lip motion in an existing video with supplied speech.
|
| 16 |
-
|
| 17 |
-
> [!WARNING]
|
| 18 |
-
> This local development package contains InsightFace face detection and landmark
|
| 19 |
-
> weights restricted to non-commercial research. LatentSync's Apache-2.0 license
|
| 20 |
-
> does not override those terms. Review upstream licenses before redistribution
|
| 21 |
-
> or deployment.
|
| 22 |
-
|
| 23 |
-
`latentsync-1.6-f32-f16.gguf` includes the temporal diffusion U-Net, Whisper Tiny
|
| 24 |
-
audio encoder, SD VAE, SCRFD face detector, 106-point landmark model, face mask,
|
| 25 |
-
configuration sidecars, and embedded audio.cpp model spec. Original mixed F32/F16
|
| 26 |
-
tensor storage is retained; inference requires no Python or ONNX Runtime.
|
| 27 |
-
|
| 28 |
-
Install FFmpeg on PATH, then run:
|
| 29 |
-
|
| 30 |
-
```bash
|
| 31 |
-
audiocpp_cli --task gen --family latentsync \
|
| 32 |
-
--model latentsync-1.6-f32-f16.gguf --backend cuda \
|
| 33 |
-
--audio speech.wav --request-option reference_video_path=speaker.mp4 \
|
| 34 |
-
--out-dir outputs/latentsync --log
|
| 35 |
-
```
|
| 36 |
-
|
| 37 |
-
The CLI writes RGB24 frames and a small JSON metadata sidecar. MP4 encoding and audio muxing
|
| 38 |
-
are separate FFmpeg steps; see `docs/models/latentsync.md` in the port's source.
|
| 39 |
-
|
| 40 |
-
## Upstream Sources
|
| 41 |
-
|
| 42 |
-
- [LatentSync weights](https://huggingface.co/ByteDance/LatentSync-1.6)
|
| 43 |
-
- [LatentSync code](https://github.com/bytedance/LatentSync/tree/a229c3948406bc2cf6eaf4873e662e70c6a04746)
|
| 44 |
-
- [SD VAE](https://huggingface.co/stabilityai/sd-vae-ft-mse)
|
| 45 |
-
- [InsightFace license](https://github.com/deepinsight/insightface#license)
|
| 46 |
-
|
| 47 |
-
This is an experimental local package, not a published release.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LatentSync-1.6-GGUF/latentsync-1.6-f32-f16.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3365364fc3761a7216969b4d474b4afd0c5892af01f6aa4ef05e63440714d283
|
| 3 |
-
size 5448376384
|
|
|
|
|
|
|
|
|
|
|
|