QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation
Paper • 2405.15863 • Published • 3
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("lichang0928/QA-MDT", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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 and this space. For more detailed instructions and the official PyTorch implementation, please refer to the project's Github repository and project page.
The model was presented in the paper QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation.
- Downloads last month
- 34