ComfyUI Node Runs on cloud
MiniMax Music3 Text Encode
Uses a MiniMax Music3 CLIP model to generate the acoustic conditioning sequence.
MiniMax Music3 Text Encode
- clip
- CONDITIONING
- seconds
◄caption—►
◄lyrics—►
◄seed0►
◄max_duration120.00►
◄cfg_scale1.5►
◄top_k50►
Categorymodel/conditioning/minimax music
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| caption | STRING | — | |
| lyrics | STRING | — | |
| seed | INT | 00–18446744073709550000 | — |
| max_duration | FLOAT | 120.000.04–360 | Maximum duration in seconds; the model can end the song earlier. |
| cfg_scale | FLOAT | 1.50–100 | — |
| top_k | INT | 501–16384 | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| CONDITIONING | CONDITIONING | — |
| seconds | FLOAT | — |