ComfyUI Node

Dia2 2B

A ComfyUI node in Runware/Audio/runware with 14 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
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)

NameTypeDefaultDescription
speechRUNWARE_SPEECH
audioSettingsoptRUNWARE_AUDIOSETTINGS
negativePromptoptSTRINGPrompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).
seedoptINT00–2147483647Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
CFGScaleoptFLOAT3.001–30Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
settings.audioTemperatureoptFLOAT0.800–5Sampling temperature for audio token generation. Lower = cleaner audio, higher = more expressive. 0 = greedy decoding.
settings.includePrefixoptBOOLEANfalseWhether to include prefix audio in the final output or trim it.
settings.temperatureoptFLOAT0.600–5Sampling temperature for text token generation. Lower = more coherent, higher = more variety. 0 = greedy decoding.
settings.topKoptINT501–500Top-K sampling for both text and audio tokens. Limits selection to K most likely tokens per step.
ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
outputFormatoptCOMBOMP3File format for the generated audio.
advanced_jsonoptSTRINGOptional JSON merged into the request. For: inputs.audios

Outputs (1)

NameTypeDescription
audioAUDIO