Downloads · 30 days
0
zachary-shah/riffusion-cnet-v3
riffusion-cnet-v3 is a machine learning model from zachary-shah. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Riffusion + ControlNet trained on 150 songs in Slakh2100 dataset for 3 days on NVIDIA A10. Generate audio from spectrogram controlled by denoised Sobel spectral edgemap, with text conditioning
Downloads · 30 days
0
Access
Public
Updated May 28, 2023
Repo size
35.3 GB
Likes
0
Public
Click a slice to open those files.
.ckpt25.6 GB · 95%
From the Hugging Face model README
Riffusion + ControlNet trained on 150 songs in Slakh2100 dataset for 3 days on NVIDIA A10. Generate audio from spectrogram controlled by denoised Sobel spectral edgemap, with text conditioning