Hayk Martiros
Hayk Martiros
Please see: https://github.com/riffusion/riffusion/blob/main/riffusion/cli.py#L19 Using the class: https://github.com/riffusion/riffusion/blob/main/riffusion/spectrogram_image_converter.py
Thanks for the tip @mthrok ! I added `libsndfile1` to the CI and it resolved the no audio backend warning. I also added it to the README and linked to...
What version of diffusers do you have installed?
I'm not sure, we should get more specific with the requirements. I believe I have 0.6.0 installed.
Are you talking about this repository or the huggingface checkpoint? This repo should not contain any checkpoints, just a few small images
I'm not sure exactly what the problem is, but as I understand storing the checkpoint as a huggingface model is totally standard, so not inclined to change it. For example...
I will do this over the weekend!
Additional fine tuning and data information has been added to the model-card. This was trained using approaches similar to hugging face examples, but fine-tuning can be achieved with very small...
Potentially you could try not tracing the UNet, if that is causing the issue: https://github.com/riffusion/riffusion-inference/blob/main/riffusion/server.py#L99 I do expect it to be too slow for real time on MPS, and not...