ALAE
jukebox
Our great sponsors
- CodiumAI - TestGPT | Generating meaningful tests for busy devs
- InfluxDB - Access the most powerful time series database as a service
- ONLYOFFICE ONLYOFFICE Docs — document collaboration in your environment
- Sonar - Write Clean Python Code. Always.
| ALAE | jukebox | |
|---|---|---|
| 1 | 127 | |
| 3,399 | 6,914 | |
| - | 4.9% | |
| 0.0 | 0.0 | |
| over 2 years ago | about 2 months ago | |
| Python | Python | |
| - | 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.
ALAE
We haven't tracked posts mentioning ALAE yet.
Tracking mentions began in Dec 2020.
jukebox
-
Why didn't OpenAI MIT license Jukebox the same way they did CLIP?
As many of you are probably aware CLIP research paper and open source code that's under MIT license underpins the entire generative image model industry. Let's not forget it's only a little over 2 years ago that this image was completely mindblowing, and now it's so basic. People took the research and released code it took off like wildfire. But Jukebox, released a year earlier, never did even though it's just as revolutionary.
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.
- 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
-
[D] Is MusicGPT a viable possibility?
There is https://openai.com/blog/jukebox/, which does generate music from prompt, but the prompt is not as detailed ("Hip Hop, in the style of Kanye West") and I don't think there is an easy way to use it online.
- AI (Visual) Art is creating a buzz. Is there AI Music?
-
ArtStation artists stage mass protest against AI-generated artwork
Jukebox AI has already been around for 2 years. Even though the results aren't that impressive, it won't be long until another AI model comes along with something better.
What are some alternatives?
lucid-sonic-dreams
spleeter - Deezer source separation library including pretrained models.
music-demixing-challenge-starter-kit - Starter kit for getting started in the Music Demixing Challenge.
ultimatevocalremovergui - GUI for a Vocal Remover that uses Deep Neural Networks.
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"
dnn_from_scratch - A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).
simsiam-cifar10 - Code to train the SimSiam model on cifar10 using PyTorch
denoising-diffusion-pytorch - Implementation of Denoising Diffusion Probabilistic Model in Pytorch
lightweight-gan - Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement