ComfyUI Node
Runware Sync 3
A ComfyUI node in Runware/Video/sync with 25 inputs and 1 output.
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)
| Name | Type | Default | Description |
|---|---|---|---|
| video | STRING | Video input (UUID or URL). | |
| speechopt | RUNWARE_SPEECH | — | |
| audioopt | STRING | Audio input (UUID or URL). | |
| numberResultsopt | INT | 11–4 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| settings.activeSpeakerDetection.autoDetectopt | BOOLEAN | false | Automatically detect and target the active speaker. |
| settings.emotionopt | COMBO | (default) | Emotional tone for performance re-animation. |
| settings.activeSpeakerDetection.frameNumberopt | BOOLEAN | false | Enable to set settings.activeSpeakerDetection.frameNumber. Off uses the model's default. |
| settings.activeSpeakerDetection.frameNumber_valueopt | INT | 0 | Frame index corresponding to the provided face coordinates. |
| settings.modeopt | COMBO | (default) | Controls the region of facial animation applied during lip sync. |
| settings.occlusionDetectionopt | BOOLEAN | false | Enable occlusion handling for obstructed faces. |
| settings.tts.provideropt | STRING | elevenlabs | Name of the TTS provider. |
| safetyopt | BOOLEAN | false | Enable to set safety. Off uses the model's default. |
| safety.checkContentopt | BOOLEAN | false | Enable or disable content safety checking. |
| safety.modeopt | COMBO | none | Safety checking mode for video generation. |
| settings.tts.similarityBoostopt | BOOLEAN | false | Enable to set settings.tts.similarityBoost. Off uses the model's default. |
| settings.tts.similarityBoost_valueopt | FLOAT | 0.000–1 | Voice similarity enforcement for the TTS provider. Higher values make the voice more closely match the target. |
| settings.tts.stabilityopt | BOOLEAN | false | Enable to set settings.tts.stability. Off uses the model's default. |
| settings.tts.stability_valueopt | FLOAT | 0.000–1 | Voice stability for the TTS provider. Higher values produce more consistent output. |
| settings.syncModeopt | COMBO | cut_off | Synchronization strategy when audio and video durations don't match. |
| settings.temperatureopt | FLOAT | 0.500–1 | Expressiveness of lip sync and facial movements. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | MP4 | File format for the generated video. |
| outputQualityopt | INT | 9520–99 | Compression quality of the output. Higher values preserve quality but increase file size. |
| advanced_jsonopt | STRING | Optional JSON merged into the request. For: settings.activeSpeakerDetection.boundingBoxes, settings.activeSpeakerDetection.coordinates, settings.segments |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |