WildAi
e20b4fd9d8
Add a dedicated loader node that loads VibeVoice checkpoints from user-provided .safetensors/.pt files in models/diffusion_models, since ComfyUI's stock Load Diffusion Model cannot detect VibeVoice architecture. The loader emits a VIBEVOICE_MODEL custom type bundle (model/processor/config/state_dict) consumed by an optional external_model input on the TTS, Realtime, and ASR nodes.
- modules/custom_types.py: VibeVoiceModel = io.Custom("VIBEVOICE_MODEL")
- modules/external_loader.py: sidecar config/preprocessor/tokenizer resolution + load_external_vibevoice_model() (TTS/streaming) and load_external_vibevoice_asr_model() (ASR); CPU-first load, in-memory state-dict injection, dtype cast, optional 4-bit quant (TTS only), SageAttention
- nodes/external_loader_node.py: VibeVoiceLoadExternalModel node
- modules/generation.py: ExternalVibeVoiceModelHandler + load_vibevoice_from_external()
- modules/asr_generation.py: ExternalVibeVoiceASRModelHandler + load_asr_from_external()
- nodes/tts_node.py, realtime_node.py, asr_node.py: optional external_model input with kind guards (streaming/ASR/TTS mismatch rejection)
- README: Loading External Models section + v2.2.0 changelog
- example_workflows/VibeVoice_external_model_example.json
- docs/plans/2026-08-16-external-model-input.md (status: COMPLETED)
Tests: +122 new/extended (test_custom_types, test_external_loader, test_external_loader_node, plus extensions to node_schema, generation, asr_generation, realtime_node, asr_node, patcher_behavioral, integration, docs_consistency, workflow, imports, extension). Full suite: 687 passed, 5 pre-existing failures, 4 skipped.
184 lines
3.3 KiB
JSON
184 lines
3.3 KiB
JSON
{
|
|
"id": "a1c2e3f4-5b6d-4e7f-8a9b-0c1d2e3f4a5b",
|
|
"revision": 0,
|
|
"last_node_id": 3,
|
|
"last_link_id": 2,
|
|
"nodes": [
|
|
{
|
|
"id": 1,
|
|
"type": "VibeVoiceLoadExternalModel",
|
|
"pos": [
|
|
-2100,
|
|
-1130
|
|
],
|
|
"size": [
|
|
340,
|
|
180
|
|
],
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "VibeVoice Model",
|
|
"type": "VIBEVOICE_MODEL",
|
|
"links": [
|
|
1
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VibeVoiceLoadExternalModel",
|
|
"cnr_id": "ComfyUI-VibeVoice"
|
|
},
|
|
"widgets_values": [
|
|
"vibevoice-1.5b.safetensors",
|
|
"VibeVoice-1.5B",
|
|
"sdpa",
|
|
false,
|
|
"auto"
|
|
],
|
|
"color": "#223",
|
|
"bgcolor": "#335"
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "VibeVoiceTTS",
|
|
"pos": [
|
|
-1570,
|
|
-1130
|
|
],
|
|
"size": [
|
|
475,
|
|
662
|
|
],
|
|
"flags": {},
|
|
"order": 1,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "external_model",
|
|
"shape": 7,
|
|
"type": "VIBEVOICE_MODEL",
|
|
"link": 1
|
|
},
|
|
{
|
|
"name": "speaker_1_voice",
|
|
"shape": 7,
|
|
"type": "AUDIO",
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "speaker_2_voice",
|
|
"shape": 7,
|
|
"type": "AUDIO",
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "speaker_3_voice",
|
|
"shape": 7,
|
|
"type": "AUDIO",
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "speaker_4_voice",
|
|
"shape": 7,
|
|
"type": "AUDIO",
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "AUDIO",
|
|
"type": "AUDIO",
|
|
"links": [
|
|
2
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VibeVoiceTTS",
|
|
"cnr_id": "ComfyUI-VibeVoice"
|
|
},
|
|
"widgets_values": [
|
|
"VibeVoice-1.5B",
|
|
"[1] This workflow loads an external VibeVoice weight file via the Load VibeVoice Model node and feeds it into the TTS node through the external_model input, overriding the model_name dropdown.",
|
|
false,
|
|
"sdpa",
|
|
1.3,
|
|
10,
|
|
42,
|
|
"fixed",
|
|
true,
|
|
0.95,
|
|
0.95,
|
|
0,
|
|
false
|
|
],
|
|
"color": "#232",
|
|
"bgcolor": "#353"
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "SaveAudio",
|
|
"pos": [
|
|
-1040,
|
|
-1130
|
|
],
|
|
"size": [
|
|
270,
|
|
112
|
|
],
|
|
"flags": {},
|
|
"order": 2,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "audio",
|
|
"type": "AUDIO",
|
|
"link": 2
|
|
}
|
|
],
|
|
"outputs": [],
|
|
"properties": {
|
|
"Node name for S&R": "SaveAudio",
|
|
"cnr_id": "comfy-core"
|
|
},
|
|
"widgets_values": [
|
|
"audio/VibeVoice_external"
|
|
]
|
|
}
|
|
],
|
|
"links": [
|
|
[
|
|
1,
|
|
1,
|
|
0,
|
|
2,
|
|
0,
|
|
"VIBEVOICE_MODEL"
|
|
],
|
|
[
|
|
2,
|
|
2,
|
|
0,
|
|
3,
|
|
0,
|
|
"AUDIO"
|
|
]
|
|
],
|
|
"groups": [],
|
|
"config": {},
|
|
"extra": {
|
|
"ds": {
|
|
"scale": 0.9,
|
|
"offset": [
|
|
2200,
|
|
1300
|
|
]
|
|
}
|
|
},
|
|
"version": 0.4
|
|
}
|