ComfyUI Node
Dia2 2B
A ComfyUI node in Runware/Audio/runware with 14 inputs and 1 output.
Dia2 2B
- speech
- audioSettings
- audio
◄negativePrompt►
◄seed0►
◄CFGScale3.00►
◄numberResults1►
◄settings.audioTemperature0.80►
◄settings.includePrefixfalse►
◄settings.temperature0.60►
◄settings.topK50►
◄ttlfalse►
◄ttl_value60►
◄outputFormatMP3►
◄advanced_json►
CategoryRunware/Audio/runware
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| speech | RUNWARE_SPEECH | — | |
| audioSettingsopt | RUNWARE_AUDIOSETTINGS | — | |
| negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| seedopt | INT | 00–2147483647 | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. |
| CFGScaleopt | FLOAT | 3.001–30 | Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt. |
| numberResultsopt | INT | 11–4 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| settings.audioTemperatureopt | FLOAT | 0.800–5 | Sampling temperature for audio token generation. Lower = cleaner audio, higher = more expressive. 0 = greedy decoding. |
| settings.includePrefixopt | BOOLEAN | false | Whether to include prefix audio in the final output or trim it. |
| settings.temperatureopt | FLOAT | 0.600–5 | Sampling temperature for text token generation. Lower = more coherent, higher = more variety. 0 = greedy decoding. |
| settings.topKopt | INT | 501–500 | Top-K sampling for both text and audio tokens. Limits selection to K most likely tokens per step. |
| 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 | MP3 | File format for the generated audio. |
| advanced_jsonopt | STRING | Optional JSON merged into the request. For: inputs.audios |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |