ComfyUI Node Runs on cloud
LTXV Reference Audio (ID-LoRA)
Set reference audio for ID-LoRA speaker identity transfer. Encodes a reference audio clip into the conditioning and optionally patches the model with identity guidance (extra forward pass without reference, amplifying the speaker identity effect).
LTXV Reference Audio (ID-LoRA)
- model
- positive
- negative
- reference_audio
- audio_vae
- MODEL
- positive
- negative
◄identity_guidance_scale3.00►
◄start_percent0.000►
◄end_percent1.000►
Categorymodel/conditioning/ltxv
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| reference_audio | AUDIO | Reference audio clip whose speaker identity to transfer. ~5 seconds recommended (training duration). Shorter or longer clips may degrade voice identity transfer. | |
| audio_vae | VAE | LTXV Audio VAE for encoding. | |
| identity_guidance_scale | FLOAT | 3.000–100 | Strength of identity guidance. Runs an extra forward pass without reference each step to amplify speaker identity. Set to 0 to disable (no extra pass). |
| start_percent | FLOAT | 0.0000–1 | Start of the sigma range where identity guidance is active. |
| end_percent | FLOAT | 1.0000–1 | End of the sigma range where identity guidance is active. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |