Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
20.17k
stars
2.01k
forks
source link
Is there "seed" in musicgen fixing to one output? #402
Newbee to music generation. Is there any thing like "seed" in image generation like stable diffusion, which could be used to fix output?
without it, it would be hard to justify the diference between large/melody models temperature, cfg, and top k top p things, with the same text prompt.
Or anyway to fix the output with same text prompt and parameters?
Newbee to music generation. Is there any thing like "seed" in image generation like stable diffusion, which could be used to fix output? without it, it would be hard to justify the diference between large/melody models temperature, cfg, and top k top p things, with the same text prompt. Or anyway to fix the output with same text prompt and parameters?