Document public AudioLift checkpoint downloads
Browse files## Summary
Link the public inference repository and document model downloads without login. Preserve checkpoint bytes and component licenses.
## Files Created / Modified
- README.md (Modified)
README.md
CHANGED
|
@@ -17,7 +17,7 @@ tags:
|
|
| 17 |
**Audio-Driven Full-Head Gaussian Avatar via Multi-view Video Generation**
|
| 18 |
|
| 19 |
This repository provides the two fine-tuned models used by AudioLift.
|
| 20 |
-
The weights are
|
| 21 |
|
| 22 |
| Model | File | Purpose |
|
| 23 |
| --- | --- | --- |
|
|
@@ -30,18 +30,21 @@ have changed. File checksums are recorded in [SHA256SUMS](SHA256SUMS).
|
|
| 30 |
## Usage
|
| 31 |
|
| 32 |
Use the AudioLift inference entrypoints in the
|
| 33 |
-
[
|
| 34 |
The entrypoints download missing models to the local `checkpoints/` directory
|
| 35 |
and verify the fine-tuned checkpoint checksums before loading them.
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
AudioLift-mvdiffusion also requires the Wan and wav2vec2 assets from
|
| 39 |
[StableAvatar](https://huggingface.co/FrancisRing/StableAvatar). These are downloaded
|
| 40 |
from the upstream model repository. AudioLift-gaussianlifter requires the camera
|
| 41 |
and model configuration files supplied with the AudioLift code.
|
| 42 |
|
| 43 |
-
These are inference checkpoints.
|
| 44 |
-
|
| 45 |
|
| 46 |
## Licenses and acknowledgements
|
| 47 |
|
|
|
|
| 17 |
**Audio-Driven Full-Head Gaussian Avatar via Multi-view Video Generation**
|
| 18 |
|
| 19 |
This repository provides the two fine-tuned models used by AudioLift.
|
| 20 |
+
The weights are publicly downloadable without a Hugging Face login.
|
| 21 |
|
| 22 |
| Model | File | Purpose |
|
| 23 |
| --- | --- | --- |
|
|
|
|
| 30 |
## Usage
|
| 31 |
|
| 32 |
Use the AudioLift inference entrypoints in the
|
| 33 |
+
[AudioLift repository](https://github.com/ZhuoyuanJiang/AudioLift).
|
| 34 |
The entrypoints download missing models to the local `checkpoints/` directory
|
| 35 |
and verify the fine-tuned checkpoint checksums before loading them.
|
| 36 |
+
To download both models and their required base assets before inference, run
|
| 37 |
+
`python scripts/download_models.py` from an installed AudioLift environment.
|
| 38 |
+
See the [installation guide](https://github.com/ZhuoyuanJiang/AudioLift/blob/main/docs/installation.md)
|
| 39 |
+
for environment setup and validation status.
|
| 40 |
|
| 41 |
AudioLift-mvdiffusion also requires the Wan and wav2vec2 assets from
|
| 42 |
[StableAvatar](https://huggingface.co/FrancisRing/StableAvatar). These are downloaded
|
| 43 |
from the upstream model repository. AudioLift-gaussianlifter requires the camera
|
| 44 |
and model configuration files supplied with the AudioLift code.
|
| 45 |
|
| 46 |
+
These are inference checkpoints. Training code is not included in the public
|
| 47 |
+
AudioLift code release.
|
| 48 |
|
| 49 |
## Licenses and acknowledgements
|
| 50 |
|