Hugging Face's logo

Comfy-Org
/
stable-audio-3

comfyui
Model card Files
xet
 Community
2
Lexius comfyanonymous commited on
Commit
3932b75
·
0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files

Co-authored-by: comfyanonymous <comfyanonymous@users.noreply.huggingface.co>

Files changed (13) hide show
  1. .gitattributes +35 -0
  2. README.md +40 -0
  3. checkpoints/stable_audio_3_medium.safetensors +3 -0
  4. checkpoints/stable_audio_3_medium_base.safetensors +3 -0
  5. checkpoints/stable_audio_3_small_music.safetensors +3 -0
  6. checkpoints/stable_audio_3_small_music_base.safetensors +3 -0
  7. checkpoints/stable_audio_3_small_sfx.safetensors +3 -0
  8. checkpoints/stable_audio_3_small_sfx_base.safetensors +3 -0
  9. text_encoders/t5gemma_b_b_ul2.safetensors +3 -0
  10. vae/same_l.json +67 -0
  11. vae/same_l.safetensors +3 -0
  12. vae/same_s.json +70 -0
  13. vae/same_s.safetensors +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license_name: custom-license
3
+ license_link: LICENSE
4
+ tags:
5
+ - comfyui
6
+ ---
7
+
8
+ # Stable Audio 3
9
+
10
+ Repackaged model files for ComfyUI.
11
+
12
+ Original model repository:
13
+
14
+ - https://huggingface.co/stabilityai/SAME-L
15
+ - https://huggingface.co/stabilityai/SAME-S
16
+ - https://huggingface.co/stabilityai/stable-audio-3-medium
17
+ - https://huggingface.co/stabilityai/stable-audio-3-medium-base
18
+ - https://huggingface.co/stabilityai/stable-audio-3-small-music
19
+ - https://huggingface.co/stabilityai/stable-audio-3-small-music-base
20
+ - https://huggingface.co/stabilityai/stable-audio-3-small-sfx
21
+ - https://huggingface.co/stabilityai/stable-audio-3-small-sfx-base
22
+
23
+ Place the files in the following folders:
24
+
25
+ ```
26
+ 📂 ComfyUI/
27
+ ├── 📂 models/
28
+ │ ├── 📂 checkpoints/
29
+ │ │ ├── stable_audio_3_medium.safetensors
30
+ │ │ ├── stable_audio_3_medium_base.safetensors
31
+ │ │ ├── stable_audio_3_small_music.safetensors
32
+ │ │ ├── stable_audio_3_small_music_base.safetensors
33
+ │ │ ├── stable_audio_3_small_sfx.safetensors
34
+ │ │ └── stable_audio_3_small_sfx_base.safetensors
35
+ │ ├── 📂 text_encoders/
36
+ │ │ └── t5gemma_b_b_ul2.safetensors
37
+ │ ├── 📂 vae/
38
+ │ │ ├── same_l.safetensors
39
+ │ │ └── same_s.safetensors
40
+ ```
checkpoints/stable_audio_3_medium.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d9c65e290e7bcd5194e0633bfc2424a59ee9683f5c2d58762d997b7d8ce0b5
3
+ size 9222116660
checkpoints/stable_audio_3_medium_base.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c443fcc4d491475064cd0ff3eb92459b1e5f5060e86d96d016f048e528e24195
3
+ size 9222116660
checkpoints/stable_audio_3_small_music.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da85866b11b01d0694d990785f6abbd79c8064df1b0e6f8aea52935e0ef84b64
3
+ size 2270384940
checkpoints/stable_audio_3_small_music_base.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79691fac2a08a99a229b98963f8377ddc78c16f5c63f7e3a022375c311093ab4
3
+ size 2270384940
checkpoints/stable_audio_3_small_sfx.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9cf1b6172f1a8c2921a9560c21109ff3239524563ced9dce6dcdef41e2f515
3
+ size 2270384940
checkpoints/stable_audio_3_small_sfx_base.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7cddb22cd7bf5e8169c6731a9eb7690c27ef5b53e8a4f9b4b2aaf8afcdaea2
3
+ size 2270384940
text_encoders/t5gemma_b_b_ul2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1eba25be8872edb0d3c6335c6658fd6388e7b14b60da6e454e404cfcd8150e
3
+ size 1187264003
vae/same_l.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "autoencoder",
3
+ "sample_size": 196608,
4
+ "sample_rate": 44100,
5
+ "audio_channels": 2,
6
+ "model": {
7
+ "pretransform": {
8
+ "type": "patched",
9
+ "config": {
10
+ "patch_size": 256,
11
+ "channels": 2
12
+ }
13
+ },
14
+ "encoder": {
15
+ "type": "same",
16
+ "requires_grad": false,
17
+ "config": {
18
+ "in_channels": 512,
19
+ "channels": 256,
20
+ "c_mults": [6],
21
+ "strides": [16],
22
+ "latent_dim": 256,
23
+ "transformer_depths": [12],
24
+ "checkpointing": true,
25
+ "differential": true,
26
+ "dyt": true,
27
+ "dim_heads": 64,
28
+ "sliding_window": [1,1],
29
+ "variable_stride": true,
30
+ "mask_noise": 0.001
31
+ }
32
+ },
33
+ "decoder": {
34
+ "type": "same",
35
+ "requires_grad": false,
36
+ "config": {
37
+ "out_channels": 512,
38
+ "channels": 256,
39
+ "c_mults": [6],
40
+ "strides": [16],
41
+ "latent_dim": 256,
42
+ "transformer_depths": [12],
43
+ "sinusoidal_blocks": [8],
44
+ "checkpointing": false,
45
+ "differential": true,
46
+ "dyt": true,
47
+ "dim_heads": 64,
48
+ "sliding_window": [1,1],
49
+ "variable_stride": true,
50
+ "mask_noise": 0.1
51
+ }
52
+ },
53
+ "bottleneck": {
54
+ "type": "softnorm",
55
+ "config": {
56
+ "dim": 256,
57
+ "noise_augment_dim": 0,
58
+ "noise_regularize": true,
59
+ "auto_scale": true,
60
+ "freeze": true
61
+ }
62
+ },
63
+ "latent_dim": 256,
64
+ "downsampling_ratio": 4096,
65
+ "io_channels": 2
66
+ }
67
+ }
vae/same_l.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf93d5345c559307fc429bde896f594516fd6a1a23014c2f6055f78d8e13378
3
+ size 3408566892
vae/same_s.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "autoencoder",
3
+ "sample_size": 24576,
4
+ "sample_rate": 44100,
5
+ "audio_channels": 2,
6
+ "model": {
7
+ "pretransform": {
8
+ "type": "patched",
9
+ "config": {
10
+ "patch_size": 256,
11
+ "channels": 2
12
+ }
13
+ },
14
+ "encoder": {
15
+ "type": "same",
16
+ "requires_grad": false,
17
+ "config": {
18
+ "in_channels": 512,
19
+ "channels": 128,
20
+ "c_mults": [6],
21
+ "strides": [16],
22
+ "latent_dim": 256,
23
+ "transformer_depths": [6],
24
+ "checkpointing": false,
25
+ "differential": true,
26
+ "dyt": true,
27
+ "dim_heads": 64,
28
+ "variable_stride": true,
29
+ "chunk_size": 32,
30
+ "chunk_midpoint_shift": true,
31
+ "mask_noise": 0.0
32
+ }
33
+ },
34
+ "decoder": {
35
+ "type": "same",
36
+ "requires_grad": false,
37
+ "config": {
38
+ "out_channels": 512,
39
+ "channels": 128,
40
+ "c_mults": [6],
41
+ "strides": [16],
42
+ "latent_dim": 256,
43
+ "transformer_depths": [6],
44
+ "sinusoidal_blocks": [0],
45
+ "checkpointing": false,
46
+ "differential": true,
47
+ "dyt": true,
48
+ "dim_heads": 64,
49
+ "variable_stride": true,
50
+ "chunk_size": 32,
51
+ "chunk_midpoint_shift": true,
52
+ "conv_mapping": true,
53
+ "mask_noise": 0.01
54
+ }
55
+ },
56
+ "bottleneck": {
57
+ "type": "softnorm",
58
+ "config": {
59
+ "dim": 256,
60
+ "noise_augment_dim": 0,
61
+ "noise_regularize": true,
62
+ "auto_scale": true,
63
+ "freeze": true
64
+ }
65
+ },
66
+ "latent_dim": 256,
67
+ "downsampling_ratio": 4096,
68
+ "io_channels": 2
69
+ }
70
+ }
vae/same_s.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19698ce3a0b462acb967ee495e9eb7945221f236968c50206cce8cf22b3d305
3
+ size 433007588