From 7a4bf02144d5670808e901974103dc82befc03a8 Mon Sep 17 00:00:00 2001 From: Shmuel Ronen <80190186+ShmuelRonen@users.noreply.github.com> Date: Tue, 3 Jun 2025 08:31:13 +0300 Subject: [PATCH] new workflow --- example_workflows/Chatterbox integration.json | 309 +++++++++++++----- 1 file changed, 232 insertions(+), 77 deletions(-) diff --git a/example_workflows/Chatterbox integration.json b/example_workflows/Chatterbox integration.json index 065ffde..164aeed 100644 --- a/example_workflows/Chatterbox integration.json +++ b/example_workflows/Chatterbox integration.json @@ -1,62 +1,30 @@ { "id": "4a7cdb14-f535-4923-861b-59ba2c7ee043", "revision": 0, - "last_node_id": 4, - "last_link_id": 3, + "last_node_id": 36, + "last_link_id": 69, "nodes": [ { - "id": 2, - "type": "ChatterboxModelLoader", + "id": 26, + "type": "LoadAudio", "pos": [ - -963.2238159179688, - 2476.6962890625 + -1472.862060546875, + 2331.7490234375 ], "size": [ 270, - 58 + 136 ], "flags": {}, "order": 0, "mode": 0, "inputs": [], - "outputs": [ - { - "name": "model", - "type": "CHATTERBOX_MODEL", - "links": [ - 1 - ] - } - ], - "properties": { - "Node name for S&R": "ChatterboxModelLoader", - "widget_ue_connectable": {} - }, - "widgets_values": [ - "auto" - ] - }, - { - "id": 3, - "type": "LoadAudio", - "pos": [ - -963.2238159179688, - 2636.142578125 - ], - "size": [ - 270, - 136 - ], - "flags": {}, - "order": 1, - "mode": 0, - "inputs": [], "outputs": [ { "name": "AUDIO", "type": "AUDIO", "links": [ - 2 + 65 ] } ], @@ -73,24 +41,96 @@ ] }, { - "id": 4, + "id": 34, + "type": "LoadAudio", + "pos": [ + -1333.963134765625, + 3007.423095703125 + ], + "size": [ + 270, + 136 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 68 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.39", + "Node name for S&R": "LoadAudio", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "male_harvey_keitel.mp3", + null, + null + ] + }, + { + "id": 35, + "type": "LoadAudio", + "pos": [ + -1328.9635009765625, + 2782.253173828125 + ], + "size": [ + 270, + 136 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 67 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.39", + "Node name for S&R": "LoadAudio", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "male_stewie.mp3", + null, + null + ] + }, + { + "id": 36, "type": "PreviewAudio", "pos": [ - -81.65412902832031, - 2511.91796875 + -542.3068237304688, + 2895.125244140625 ], "size": [ 270, 88 ], "flags": {}, - "order": 3, + "order": 6, "mode": 0, "inputs": [ { "name": "audio", "type": "AUDIO", - "link": 3 + "link": 69 } ], "outputs": [], @@ -103,30 +143,55 @@ "widgets_values": [] }, { - "id": 1, - "type": "ChatterboxGenerate", + "id": 15, + "type": "PreviewAudio", "pos": [ - -561.8939819335938, - 2513.0498046875 + -517.1994018554688, + 2329.54736328125 ], "size": [ - 443.0075988769531, - 342.5619812011719 + 270, + 88 ], "flags": {}, - "order": 2, + "order": 5, "mode": 0, "inputs": [ { - "name": "model", - "type": "CHATTERBOX_MODEL", - "link": 1 - }, + "name": "audio", + "type": "AUDIO", + "link": 66 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.39", + "Node name for S&R": "PreviewAudio", + "widget_ue_connectable": {} + }, + "widgets_values": [] + }, + { + "id": 33, + "type": "ChatterboxTTS", + "pos": [ + -1068.8953857421875, + 2262.755126953125 + ], + "size": [ + 400, + 256 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ { "name": "reference_audio", "shape": 7, "type": "AUDIO", - "link": 2 + "link": 65 } ], "outputs": [ @@ -134,57 +199,147 @@ "name": "audio", "type": "AUDIO", "links": [ - 3 + 66 ] } ], "properties": { - "Node name for S&R": "ChatterboxGenerate", + "Node name for S&R": "ChatterboxTTS", "widget_ue_connectable": {} }, "widgets_values": [ - "We're excited to introduce Chatterbox, Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.", - 0.5000000000000001, - 0.5000000000000001, - 0.4000000000000001 + "Hello world! This is ChatterboxTTS in ComfyUI.", + "auto", + 0.5, + 0.8, + 0.5, + 3298238449, + "randomize", + "" + ] + }, + { + "id": 32, + "type": "ChatterboxVC", + "pos": [ + -897.5169677734375, + 2895.12451171875 + ], + "size": [ + 282.7749938964844, + 78 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "name": "source_audio", + "type": "AUDIO", + "link": 67 + }, + { + "name": "target_audio", + "type": "AUDIO", + "link": 68 + } + ], + "outputs": [ + { + "name": "converted_audio", + "type": "AUDIO", + "links": [ + 69 + ] + } + ], + "properties": { + "Node name for S&R": "ChatterboxVC", + "widget_ue_connectable": {} + }, + "widgets_values": [ + "auto" ] } ], "links": [ [ - 1, - 2, + 65, + 26, 0, - 1, + 33, 0, - "CHATTERBOX_MODEL" + "AUDIO" ], [ - 2, - 3, + 66, + 33, 0, - 1, + 15, + 0, + "AUDIO" + ], + [ + 67, + 35, + 0, + 32, + 0, + "AUDIO" + ], + [ + 68, + 34, + 0, + 32, 1, "AUDIO" ], [ - 3, - 1, + 69, + 32, 0, - 4, + 36, 0, "AUDIO" ] ], - "groups": [], + "groups": [ + { + "id": 2, + "title": "ChatterBox Text-to-Speech", + "bounding": [ + -1513.438720703125, + 2120.572021484375, + 1376.1483154296875, + 501.39434814453125 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "ChatterBox Voice Conversion", + "bounding": [ + -1510.47412109375, + 2652.15234375, + 1371.289794921875, + 575.38330078125 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], "config": {}, "extra": { "ue_links": [], "ds": { - "scale": 1.0610764609500007, + "scale": 0.9646149645000006, "offset": [ - 1352.2323485226436, - -2229.4752654838985 + 1979.2684697096672, + -2096.12660280401 ] }, "links_added_by_ue": [],