sample-generator
jukebox
sample-generator | jukebox | |
---|---|---|
9 | 129 | |
1,047 | 7,580 | |
0.0% | 0.6% | |
2.9 | 0.0 | |
about 1 year ago | 2 days ago | |
Jupyter Notebook | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sample-generator
-
Generative AI
yes, Harmon.ai 's Dance Diffusion https://github.com/Harmonai-org/sample-generator
-
Should we as producers be worried about AI?
Here's my take. AI is coming, whether you like it or not. In some respects it's already here. Take a look at Dance Diffusion, https://github.com/Harmonai-org/sample-generator a tool that can generate endless new samples for you at the click of a button. We aren't at the point yet where it can generate full songs, but within a few months we will get there. The team that developed Dance Diffusion is doing some amazing work in this space, and I suggest that you learn about it ASAP if you don't want to get left behind. Worrying about stuff like this is ultimately pointless because it's coming whether you like it or not, and while I know it sounds a bit harsh to say, you should learn the tools that are available and use them to your advantage. Think of this more as a creative partner that you can bounce ideas off of, someone to collaborate with. It's just helping you come up with new ideas, not completely replacing you as a producer and engineer. Just relax, and have fun with it.
-
Where is the StableDiffusion of music making ?
Harmonai from Stability AI has done a lot of work on music. There is a dedicated Discord , a github for their Dance Diffusion , and even a live 24/7 YT stream of their generated music
- AI (Visual) Art is creating a buzz. Is there AI Music?
-
AI music generator?
Have a look at Dance Diffusion from Harmonai (which is a project from Stability AI). There's also a Discord for it and a Collab for you to try.
- Stable Diffusion links from around September 28, 2022 that I collected for further processing
- Dance Diffusion is out!
- I wrote a comprehensive guide on how to use Dance Diffusion AI to generate sounds.
-
AI-Generated Artwork Won First Place at a State Fair Fine Arts Competition, and Artists Are Pissed
That's a good attitude to have, more people should adopt it. Here's a treat for ya https://github.com/Harmonai-org/sample-generator. This is going to be the next big I believe thing once the team finaddles with it some more.
jukebox
-
Open Source Libraries
openai/jukebox: Music Generation
- Will AI be able to create similar sounding music based off input?
-
Best model for music generation?
https://github.com/openai/jukebox The demo code is there.
-
Why didn't OpenAI MIT license Jukebox the same way they did CLIP?
I didn't even know about it until I heard Sam Altman casually mention it in an interview, I was expecting some basic tunes generator, but this is so amazing! I mean yeah the voices are not clear, it's muffled, but look at how far have image models progressed, if you applied the same amount of collaborative effort here, the results could be amazing! ElevenLabs showed how good and clear can AI-created voices sound. The only reason I can think of is that the Jukebox code is under view license only.
-
[R] [N] Noise2Music - Diffusion models for generating high quality music audio from text prompts, by Google Research
OpenAI had this figured out 3 years ago: https://openai.com/blog/jukebox/ . You could then even define your own text. Model is open source too.
-
Is music next?
They've had jukebox for a few years now, so I'm sure some new model will get released and explode overnight, like what chatGPT did.
-
Mongolian Gabba Goat Techno
That already exists
- El éxito continuo de OpenAI: Y como llegaron a crear la IA más avanzada del 2023. ChatGPT.
-
Implementation of Google's MusicLM in PyTorch
This model is designed to output raw audio.
However, there are many models which do output midi. That's actually much simpler, and has been done already a few years ago.
I thought OpenAI did this. But then, I might misremember, because their Jukebox actually also seems to produce raw audio (https://openai.com/blog/jukebox/).
However, midi generation is so easy, you even find it in some tutorials: https://www.tensorflow.org/tutorials/audio/music_generation
- FREE AI THINGS
What are some alternatives?
CRASH
lucid-sonic-dreams
Sample-Diffusion-Gradio - Gradio client for harmonai sample diffusion.
ultimatevocalremovergui - GUI for a Vocal Remover that uses Deep Neural Networks.
stable-diffusion-webui - Stable Diffusion web UI
spleeter - Deezer source separation library including pretrained models.
music-demixing-challenge-starter-kit - Starter kit for getting started in the Music Demixing Challenge.
dalle-mini - DALL·E Mini - Generate images from a text prompt
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
ALAE - [CVPR2020] Adversarial Latent Autoencoders
musiclm-pytorch - Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch