Files
1038lab-ComfyUI-MegaTTS/example_workflows/Comfyui-MegaTTS-NodeSamples.json
T
2025-04-11 16:45:51 -07:00

285 lines
5.1 KiB
JSON

{
"id": "00000000-0000-0000-0000-000000000000",
"revision": 0,
"last_node_id": 15,
"last_link_id": 7,
"nodes": [
{
"id": 9,
"type": "MegaTTS3",
"pos": [
-432.67822265625,
-141
],
"size": [
400,
208
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "generated_audio",
"type": "AUDIO",
"links": [
5
]
}
],
"properties": {
"Node name for S&R": "MegaTTS3"
},
"widgets_values": [
"",
"en",
32,
1.4,
3,
"00003.wav"
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 13,
"type": "PreviewAudio",
"pos": [
4.32177734375,
123
],
"size": [
315,
88
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 6
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.27",
"Node name for S&R": "PreviewAudio"
},
"widgets_values": [
""
]
},
{
"id": 10,
"type": "MegaTTS3S",
"pos": [
-432.67822265625,
123
],
"size": [
400,
200
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "generated_audio",
"type": "AUDIO",
"links": [
6
]
}
],
"properties": {
"Node name for S&R": "MegaTTS3S"
},
"widgets_values": [
"",
"en",
"00003.wav"
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 12,
"type": "PreviewAudio",
"pos": [
4.32177734375,
-141
],
"size": [
315,
88
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 5
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.27",
"Node name for S&R": "PreviewAudio"
},
"widgets_values": [
""
]
},
{
"id": 14,
"type": "LoadAudio",
"pos": [
-1127.67822265625,
-141
],
"size": [
315,
136
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
7
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.27",
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"dt.mp3",
"",
""
]
},
{
"id": 11,
"type": "MegaTTS_VoiceMaker",
"pos": [
-783.67822265625,
-141
],
"size": [
315,
204
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "audio_in",
"type": "AUDIO",
"link": 7
}
],
"outputs": [
{
"name": "audio_out",
"type": "AUDIO",
"links": null
},
{
"name": "voice_path",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "MegaTTS_VoiceMaker"
},
"widgets_values": [
"my_voice",
"",
true,
true,
10
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 15,
"type": "MarkdownNote",
"pos": [
-928.1925048828125,
128.2677764892578
],
"size": [
462,
163
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
" \n> The WaveVAE encoder is currently not available. \n>\n> For security reasons, Bytedance has not uploaded the WaveVAE encoder.\n>\n> You can only use pre-extracted latents (.npy files) for inference. \n>\n> To synthesize speech for a specific speaker, ensure both the corresponding WAV and NPY files are in the same directory.\n>\n> Refer to the [Bytedance MegaTTS3 repository](https://github.com/bytedance/MegaTTS3) for details on obtaining necessary files or submitting your voice samples."
],
"color": "#432",
"bgcolor": "#653"
}
],
"links": [
[
5,
9,
0,
12,
0,
"AUDIO"
],
[
6,
10,
0,
13,
0,
"AUDIO"
],
[
7,
14,
0,
11,
0,
"AUDIO"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 1.6105100000000008,
"offset": [
1484.4692640034007,
104.43643938876491
]
}
},
"version": 0.4
}