niobures commited on
Commit
10b3570
·
verified ·
1 Parent(s): ab109ea
Files changed (34) hide show
  1. .gitattributes +11 -0
  2. MMAudio.zip +3 -0
  3. forks/MMAudio [fblissjr] +2 -27.zip +3 -0
  4. forks/MMAudio [zsxkib] (replicate +2 -13).zip +3 -0
  5. notebooks/MMAudio_Demo.ipynb +0 -0
  6. notebooks/mmaudio.ipynb +131 -0
  7. notebooks/Источники.txt +4 -0
  8. releases/v0.1/.gitattributes +36 -0
  9. releases/v0.1/MMAudio-0.1.zip +3 -0
  10. releases/v0.1/README.md +8 -0
  11. releases/v0.1/model/best_netG.pt +3 -0
  12. releases/v0.1/model/examples/hunyuan_spring.mp4 +3 -0
  13. releases/v0.1/model/examples/hunyuan_typing.mp4 +3 -0
  14. releases/v0.1/model/examples/hunyuan_wake_up.mp4 +3 -0
  15. releases/v0.1/model/examples/mochi_storm.mp4 +3 -0
  16. releases/v0.1/model/examples/sora_beach.mp4 +3 -0
  17. releases/v0.1/model/examples/sora_galloping.mp4 +3 -0
  18. releases/v0.1/model/examples/sora_india.mp4 +3 -0
  19. releases/v0.1/model/examples/sora_kraken.mp4 +3 -0
  20. releases/v0.1/model/examples/sora_nyc.mp4 +3 -0
  21. releases/v0.1/model/examples/sora_seahorse.mp4 +3 -0
  22. releases/v0.1/model/examples/sora_serpent.mp4 +3 -0
  23. releases/v0.1/model/ext_weights/best_netG.pt +3 -0
  24. releases/v0.1/model/ext_weights/synchformer_state_dict.pth +3 -0
  25. releases/v0.1/model/ext_weights/v1-16.pth +3 -0
  26. releases/v0.1/model/ext_weights/v1-44.pth +3 -0
  27. releases/v0.1/model/synchformer_state_dict.pth +3 -0
  28. releases/v0.1/model/v1-16.pth +3 -0
  29. releases/v0.1/model/v1-44.pth +3 -0
  30. releases/v0.1/model/weights/mmaudio_large_44k.pth +3 -0
  31. releases/v0.1/model/weights/mmaudio_large_44k_v2.pth +3 -0
  32. releases/v0.1/model/weights/mmaudio_medium_44k.pth +3 -0
  33. releases/v0.1/model/weights/mmaudio_small_16k.pth +3 -0
  34. releases/v0.1/model/weights/mmaudio_small_44k.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,14 @@ saved_model/**/* 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
 
 
 
 
 
 
 
 
 
 
 
 
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
36
+ releases/v0.1/model/examples/hunyuan_spring.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ releases/v0.1/model/examples/hunyuan_typing.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ releases/v0.1/model/examples/hunyuan_wake_up.mp4 filter=lfs diff=lfs merge=lfs -text
39
+ releases/v0.1/model/examples/mochi_storm.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ releases/v0.1/model/examples/sora_beach.mp4 filter=lfs diff=lfs merge=lfs -text
41
+ releases/v0.1/model/examples/sora_galloping.mp4 filter=lfs diff=lfs merge=lfs -text
42
+ releases/v0.1/model/examples/sora_india.mp4 filter=lfs diff=lfs merge=lfs -text
43
+ releases/v0.1/model/examples/sora_kraken.mp4 filter=lfs diff=lfs merge=lfs -text
44
+ releases/v0.1/model/examples/sora_nyc.mp4 filter=lfs diff=lfs merge=lfs -text
45
+ releases/v0.1/model/examples/sora_seahorse.mp4 filter=lfs diff=lfs merge=lfs -text
46
+ releases/v0.1/model/examples/sora_serpent.mp4 filter=lfs diff=lfs merge=lfs -text
MMAudio.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd190a013ced93e499b06bdcc8595d3c637d527c690b778de5f7a8129436dc1
3
+ size 270800
forks/MMAudio [fblissjr] +2 -27.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209082ec3efb6234b47051fa4e56fc52a81557cdcffff5a9316520eca0114f71
3
+ size 244981
forks/MMAudio [zsxkib] (replicate +2 -13).zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe34287b35ed88ae9a5c22d542af96d26ad3bf281059317f2f72aa41b66b1485
3
+ size 252162
notebooks/MMAudio_Demo.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
notebooks/mmaudio.ipynb ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": [],
7
+ "gpuType": "T4"
8
+ },
9
+ "kernelspec": {
10
+ "name": "python3",
11
+ "display_name": "Python 3"
12
+ },
13
+ "language_info": {
14
+ "name": "python"
15
+ },
16
+ "accelerator": "GPU"
17
+ },
18
+ "cells": [
19
+ {
20
+ "cell_type": "markdown",
21
+ "source": [
22
+ "Follow my instagram : https://www.instagram.com/xsocialandapps"
23
+ ],
24
+ "metadata": {
25
+ "id": "8UCd9oLtSkK9"
26
+ }
27
+ },
28
+ {
29
+ "cell_type": "markdown",
30
+ "source": [
31
+ "## Install dependencies"
32
+ ],
33
+ "metadata": {
34
+ "id": "nq1Ytxi_gJnh"
35
+ }
36
+ },
37
+ {
38
+ "cell_type": "code",
39
+ "source": [
40
+ "%cd /content\n",
41
+ "!git clone https://github.com/zachysaur/MMAudio.git\n",
42
+ "%cd /content/MMAudio\n",
43
+ "!pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n",
44
+ "!pip install -e ."
45
+ ],
46
+ "metadata": {
47
+ "id": "tTiNYTWSgJKB"
48
+ },
49
+ "execution_count": null,
50
+ "outputs": []
51
+ },
52
+ {
53
+ "cell_type": "markdown",
54
+ "source": [
55
+ "# Upload Video"
56
+ ],
57
+ "metadata": {
58
+ "id": "NmJDTxMGhQdi"
59
+ }
60
+ },
61
+ {
62
+ "cell_type": "code",
63
+ "source": [
64
+ "from IPython.display import HTML\n",
65
+ "from base64 import b64encode\n",
66
+ "import ipywidgets as widgets\n",
67
+ "from IPython.display import display\n",
68
+ "\n",
69
+ "# Create a file upload widget\n",
70
+ "upload_widget = widgets.FileUpload(accept=\".mp4\", multiple=False)\n",
71
+ "\n",
72
+ "# Function to display the uploaded video\n",
73
+ "def display_video(change):\n",
74
+ " for file_name, file_info in upload_widget.value.items():\n",
75
+ " # Save the uploaded file\n",
76
+ " with open(file_name, 'wb') as f:\n",
77
+ " f.write(file_info['content'])\n",
78
+ "\n",
79
+ " # Convert the video to a base64 data URL\n",
80
+ " data_url = \"data:video/mp4;base64,\" + b64encode(open(file_name, 'rb').read()).decode()\n",
81
+ " display(HTML(f\"\"\"\n",
82
+ " <video width=400 controls>\n",
83
+ " <source src=\"{data_url}\" type=\"video/mp4\">\n",
84
+ " </video>\n",
85
+ " \"\"\"))\n",
86
+ "\n",
87
+ "# Observe changes to the upload widget\n",
88
+ "upload_widget.observe(display_video, names='value')\n",
89
+ "\n",
90
+ "# Display the widget\n",
91
+ "display(upload_widget)"
92
+ ],
93
+ "metadata": {
94
+ "id": "3SYoUcUghlal"
95
+ },
96
+ "execution_count": null,
97
+ "outputs": []
98
+ },
99
+ {
100
+ "cell_type": "markdown",
101
+ "source": [
102
+ "\n",
103
+ "# Prompt and Result"
104
+ ],
105
+ "metadata": {
106
+ "id": "v_BM2f7niHm1"
107
+ }
108
+ },
109
+ {
110
+ "cell_type": "code",
111
+ "source": [
112
+ "!python demo.py --duration=10 --video=322875732015239177.mp4 --prompt \"Parrott singing ana song\"\n",
113
+ "\n",
114
+ "\n",
115
+ "from IPython.display import HTML\n",
116
+ "from base64 import b64encode\n",
117
+ "data_url = \"data:video/mp4;base64,\" + b64encode(open('./output/322875732015239177.mp4', 'rb').read()).decode()\n",
118
+ "HTML(\"\"\"\n",
119
+ "<video width=400 controls>\n",
120
+ " <source src=\"%s\" type=\"video/mp4\">\n",
121
+ "</video>\n",
122
+ "\"\"\" % data_url)"
123
+ ],
124
+ "metadata": {
125
+ "id": "xnhmnCkJiiAU"
126
+ },
127
+ "execution_count": null,
128
+ "outputs": []
129
+ }
130
+ ]
131
+ }
notebooks/Источники.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Блокнот Источник
2
+ -----------------------------------------------------------------------
3
+ mmaudio.ipynb https://github.com/zachysaur/Google
4
+ MMAudio_Demo.ipynb https://github.com/hkchengrex/MMAudio (https://colab.research.google.com/drive/1TAaXCY2-kPk4xE4PwKB3EqFbSnkUuzZ8?usp=sharing)
releases/v0.1/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
36
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
releases/v0.1/MMAudio-0.1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a00686de9d159140f4f78fd9971dbbab4fd95bbc29129cd812b8f6df9bc99ba
3
+ size 115361
releases/v0.1/README.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ ---
6
+ Code: https://github.com/hkchengrex/MMAudio
7
+ license: mit
8
+ ---
releases/v0.1/model/best_netG.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970ca75ee4d5ce583e9396a4534acb14971ea2b4f1c22e038f476680c868a789
3
+ size 449217313
releases/v0.1/model/examples/hunyuan_spring.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e268461241bffa5d7283bda9360a89c794a5795a0f1fc6c6b891509e16fa9b55
3
+ size 2963746
releases/v0.1/model/examples/hunyuan_typing.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6cda8a4f2d984535b634635d5243ba03e00963f575eb92cc2367651ca78eba
3
+ size 255335
releases/v0.1/model/examples/hunyuan_wake_up.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bdb18b8681472e0757fccf1aaec7538909e669819a71fc0eb8d5c9de449979
3
+ size 1049356
releases/v0.1/model/examples/mochi_storm.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2a3be076dfcda825320cb1a4d91a5247888dc07745291c5145c6c0dcea0b90
3
+ size 2391821
releases/v0.1/model/examples/sora_beach.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a2bab57e0d2ba03d4661647c9acb71135441eb48ab81360df18bf02753a96d
3
+ size 868646
releases/v0.1/model/examples/sora_galloping.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d482dcd283e8523d96a001a705d14626a26989db7270815e1d2bf00eff9d9a0e
3
+ size 867259
releases/v0.1/model/examples/sora_india.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29bee8510cad7335bd74651f89cd5299445a66d12d6382ff4130dd55b06fcde7
3
+ size 875528
releases/v0.1/model/examples/sora_kraken.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc280c3dbaf806b0fa721932c00d830514209341846e6e3171aafd98e332fed
3
+ size 1043462
releases/v0.1/model/examples/sora_nyc.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3519c769004a14e4ef297b7ba4342880ee48e61af687cab1f71c01265290ccaa
3
+ size 7416907
releases/v0.1/model/examples/sora_seahorse.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385b7b3789d0089b475b6d442b851d465576ae3ee26f311eb0cd7f657b5a3382
3
+ size 3524096
releases/v0.1/model/examples/sora_serpent.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ced1b9966f3e0f3c2181432d7412f71ea1fcf6b50a59b5f91076b08f79003258
3
+ size 2102552
releases/v0.1/model/ext_weights/best_netG.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970ca75ee4d5ce583e9396a4534acb14971ea2b4f1c22e038f476680c868a789
3
+ size 449217313
releases/v0.1/model/ext_weights/synchformer_state_dict.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aff082f2df5c3bc52759db0c865c7ee772ae6400b860d1b7e90413f2defb67c
3
+ size 950058171
releases/v0.1/model/ext_weights/v1-16.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ad082c714ccf3771898a771fc6eebdc1d9c8d5c6154726906a97f43603d62c
3
+ size 686652758
releases/v0.1/model/ext_weights/v1-44.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6cc15dc31947675f75c950c41f4dcfd0d6d1817555ac871f809ec388e4651a
3
+ size 1221942998
releases/v0.1/model/synchformer_state_dict.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aff082f2df5c3bc52759db0c865c7ee772ae6400b860d1b7e90413f2defb67c
3
+ size 950058171
releases/v0.1/model/v1-16.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ad082c714ccf3771898a771fc6eebdc1d9c8d5c6154726906a97f43603d62c
3
+ size 686652758
releases/v0.1/model/v1-44.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6cc15dc31947675f75c950c41f4dcfd0d6d1817555ac871f809ec388e4651a
3
+ size 1221942998
releases/v0.1/model/weights/mmaudio_large_44k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3094f49ec67847dc5cf989982033b674574fd35f313d2fe4e54de8998a576dd
3
+ size 4120388840
releases/v0.1/model/weights/mmaudio_large_44k_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6bf693424fbd4ce0244fff8c412347714d5ac586e28dbeffadfa0f2b647af74
3
+ size 4122474715
releases/v0.1/model/weights/mmaudio_medium_44k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6b01b5767a92f71529474faffedca2309416ff822b57b0c8d18be218cfb41a
3
+ size 2487535109
releases/v0.1/model/weights/mmaudio_small_16k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61987bcbd6fc689af063075d7efaef29425f65df155dac589c07fa8173a03c1c
3
+ size 629395261
releases/v0.1/model/weights/mmaudio_small_44k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd92e860a58f0fac972706dd06034e49dceff2e1450bbde5703785c812b0f1
3
+ size 629946624