ComfyUI Node
HeartMuLa Style Embed
A ComfyUI node in JK-HeartMuLa with 7 inputs and 1 output.
HeartMuLa Style Embed
- muq_model
- audio_input
- cmuq
◄enabletrue►
◄free_vram_aftertrue►
◄normalizetrue►
◄audio▾►
◄style_strength1.00►
CategoryJK-HeartMuLa
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| muq_model | JKHEARTMULA_MUQ | — | |
| enable | BOOLEAN | true | When off, output a zero embedding (no style transfer) -- identical to style_strength = 0. Lets a single switch toggle style transfer on/off in a shared workflow without rewiring. |
| free_vram_after | BOOLEAN | true | After embedding, offload MuQ-MuLan back to CPU and free its VRAM so the HeartMuLa models have room to generate. No effect when MuQ runs on CPU. It stays cached in RAM (no reload), and is moved back to the chosen device automatically on the next embed. |
| normalize | BOOLEAN | true | Re-normalize the reference embedding to unit length before applying style_strength, so the strength is consistent regardless of reference length. (MuQ averages 10s clips, so a longer reference otherwise yields a weaker vector.) Recommended on. |
| audio | COMBO | Reference audio (drag-drop or upload). Ignored if the 'audio_input' socket is connected. | |
| style_strength | FLOAT | 1.000–2 | Style influence. 0 = off (no style), 1.0 = natural/calibrated, >1 over-drives (can destabilize -- short/subdued output). Drag or type a value. |
| audio_inputopt | AUDIO | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| cmuq | JKHEARTMULA_CMUQ | — |