There's a specific model for stable diffusion called riffusion that does an okay job. If you want to play with it I recommend downloading the automatic 1111 client and installing it from the "plugins" tab.

Huggingface is the place to look for that: https://huggingface.co/docs/transformers/model_doc/musicgen Not quite free, but free to use.

I've been using audio webui which supports generating through musicgen