TangoFlux
TangoFlux consists of FluxTransformer blocks which are Diffusion Transformer (DiT) and Multimodal Diffusion Transformer (MMDiT), conditioned on textual prompt and duration embedding to generate audio at 44.1kHz up to 30 seconds.
text → audio · made by Deep Cognition and Language Research (DeCLaRe) Lab
Sold by
Nobody in the catalogue publishes a price for this yet.
About
TangoFlux — an audio model from Deep Cognition and Language Research (DeCLaRe) Lab.
It takes text and returns audio. It was published in December 2024. The catalogue files it under speak.
Every current figure
- Maker
- Deep Cognition and Language Research (DeCLaRe) Lab
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- December 2024
Known as 1 name
declare-lab/TangoFlux