riffusion-inference VS riffusion

Just put the generated image into the seeds folder on the inference server, replace it with one of them on the seed_images folder: https://github.com/hmartiro/riffusion-inference/tree/main/seed_images

I think so. This is the specific code they say they use to do the image>audio conversion

I'm still reading, but it looks like they're doing some extra pre and post processing: https://github.com/hmartiro/riffusion-inference

Yes from https://huggingface.co/runwayml/stable-diffusion-v1-5. Our checkpoint works with automatic1111, and if you'd like to make an extension to decode to audio, it should be pretty straightforward: https://github.com/hmartiro/riffusion-inference/blob/main/ri...

Why don’t you try Riffusion? https://github.com/riffusion/riffusion The general idea is convert your audio waveform into an image (spectrogram).

riffusion - uses stable diffusion to generate spectrograms as images and converts them into audio. There's an online demo you can try. Not sure how easy it is to make full length songs as each image generated is about 5 seconds of audio. The demo sort of does it.

Stable diffusion for real-time music generation:

https://github.com/riffusion/riffusion

https://github.com/riffusion/riffusion-app

I'm using the (Vanilla?) Riffusion + App https://github.com/riffusion/riffusion https://github.com/riffusion/riffusion-app

Riffusion: https://github.com/riffusion/riffusion

There's a riffusion app you can run locally.

Well, if you've got Stable Diffusion running, you should be able to run Riffusion.