ComfyUI Node

Runware Sync 3

A ComfyUI node in Runware/Video/sync with 25 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
Runware Sync 3
  • speech
  • video
video
audio
numberResults1
settings.activeSpeakerDetection.autoDetectfalse
settings.emotion(default)
settings.activeSpeakerDetection.frameNumberfalse
settings.activeSpeakerDetection.frameNumber_value0
settings.mode(default)
settings.occlusionDetectionfalse
settings.tts.providerelevenlabs
safetyfalse
safety.checkContentfalse
safety.modenone
settings.tts.similarityBoostfalse
settings.tts.similarityBoost_value0.00
settings.tts.stabilityfalse
settings.tts.stability_value0.00
settings.syncModecut_off
settings.temperature0.50
ttlfalse
ttl_value60
outputFormatMP4
outputQuality95
advanced_json
CategoryRunware/Video/sync

Inputs (25)

NameTypeDefaultDescription
videoSTRINGVideo input (UUID or URL).
speechoptRUNWARE_SPEECH
audiooptSTRINGAudio input (UUID or URL).
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
settings.activeSpeakerDetection.autoDetectoptBOOLEANfalseAutomatically detect and target the active speaker.
settings.emotionoptCOMBO(default)Emotional tone for performance re-animation.
settings.activeSpeakerDetection.frameNumberoptBOOLEANfalseEnable to set settings.activeSpeakerDetection.frameNumber. Off uses the model's default.
settings.activeSpeakerDetection.frameNumber_valueoptINT0Frame index corresponding to the provided face coordinates.
settings.modeoptCOMBO(default)Controls the region of facial animation applied during lip sync.
settings.occlusionDetectionoptBOOLEANfalseEnable occlusion handling for obstructed faces.
settings.tts.provideroptSTRINGelevenlabsName of the TTS provider.
safetyoptBOOLEANfalseEnable to set safety. Off uses the model's default.
safety.checkContentoptBOOLEANfalseEnable or disable content safety checking.
safety.modeoptCOMBOnoneSafety checking mode for video generation.
settings.tts.similarityBoostoptBOOLEANfalseEnable to set settings.tts.similarityBoost. Off uses the model's default.
settings.tts.similarityBoost_valueoptFLOAT0.000–1Voice similarity enforcement for the TTS provider. Higher values make the voice more closely match the target.
settings.tts.stabilityoptBOOLEANfalseEnable to set settings.tts.stability. Off uses the model's default.
settings.tts.stability_valueoptFLOAT0.000–1Voice stability for the TTS provider. Higher values produce more consistent output.
settings.syncModeoptCOMBOcut_offSynchronization strategy when audio and video durations don't match.
settings.temperatureoptFLOAT0.500–1Expressiveness of lip sync and facial movements.
ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
outputFormatoptCOMBOMP4File format for the generated video.
outputQualityoptINT9520–99Compression quality of the output. Higher values preserve quality but increase file size.
advanced_jsonoptSTRINGOptional JSON merged into the request. For: settings.activeSpeakerDetection.boundingBoxes, settings.activeSpeakerDetection.coordinates, settings.segments

Outputs (1)

NameTypeDescription
videoVIDEO