Upload 2 files
Browse files
LongCatAudio/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "LongCatAudioDiTVae",
|
| 3 |
+
"_diffusers_version": "0.38.0.dev0",
|
| 4 |
+
"act_fn": null,
|
| 5 |
+
"c_mults": [
|
| 6 |
+
1,
|
| 7 |
+
2,
|
| 8 |
+
4,
|
| 9 |
+
8,
|
| 10 |
+
16
|
| 11 |
+
],
|
| 12 |
+
"channels": 128,
|
| 13 |
+
"downsample_shortcut": "averaging",
|
| 14 |
+
"downsampling_ratio": 2048,
|
| 15 |
+
"encoder_latent_dim": 128,
|
| 16 |
+
"final_tanh": false,
|
| 17 |
+
"in_channels": 1,
|
| 18 |
+
"in_shortcut": "duplicating",
|
| 19 |
+
"latent_dim": 64,
|
| 20 |
+
"out_shortcut": "averaging",
|
| 21 |
+
"sample_rate": 24000,
|
| 22 |
+
"scale": 0.71,
|
| 23 |
+
"strides": [
|
| 24 |
+
2,
|
| 25 |
+
4,
|
| 26 |
+
4,
|
| 27 |
+
8,
|
| 28 |
+
8
|
| 29 |
+
],
|
| 30 |
+
"upsample_shortcut": "duplicating",
|
| 31 |
+
"use_snake": true
|
| 32 |
+
}
|
LongCatAudio/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f46bc743439b6ffce657b5805ec5d8214204c0aaf6cf6426a8b66b8cc8356b3
|
| 3 |
+
size 624466876
|