| datasets: | |
| - seungheondoh/LP-MusicCaps-MSD | |
| - DynamicSuperb/MusicGenreClassification_FMA | |
| - DynamicSuperb/MARBLEMusicTagging_MagnaTagATune | |
| - agkphysics/AudioSet | |
| language: | |
| - en | |
| license: mit | |
| pipeline_tag: text-to-audio | |
| tags: | |
| - music | |
| - art | |
| - text-to-audio | |
| model_type: diffusers | |
| library_name: diffusers | |
| ## Model Description | |
| This model, QA-MDT, allows for easy setup and usage for generating music from text prompts. It incorporates a quality-aware training strategy to improve the fidelity of generated music. | |
| ## How to Use | |
| A Hugging Face Diffusers implementation is available at [this model](https://huggingface.co/jadechoghari/openmusic) and [this space](https://huggingface.co/spaces/jadechoghari/OpenMusic). For more detailed instructions and the official PyTorch implementation, please refer to the project's [Github repository](https://github.com/ivcylc/qa-mdt) and [project page](https://qa-mdt.github.io/). | |
| The model was presented in the paper [QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation](https://huggingface.co/papers/2405.15863). |