| license: cc-by-nc-4.0 | |
| The release archives that the [Woosh-DFlow](https://huggingface.co/spaces/teamup-tech/Woosh-DFlow) Space unpacks into its image, mirrored from the [v1.0.0 release](https://github.com/SonyResearch/Woosh/releases/tag/v1.0.0) of [Woosh](https://github.com/SonyResearch/Woosh) by Sony AI. The archives are unchanged, each extracting to its own `checkpoints/<name>` folder. | |
| - `Woosh-DFlow.zip`: the distilled latent diffusion model | |
| - `Woosh-AE.zip`: the audio autoencoder | |
| - `TextConditionerA.zip`: the audio-CLAP text conditioner | |
| The weights are licensed [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/), so they may be used non-commercially only, with attribution to Sony AI. | |