descript-audio-codec
pytorch-CycleGAN-and-pix2pix
descript-audio-codec | pytorch-CycleGAN-and-pix2pix | |
---|---|---|
2 | 10 | |
917 | 22,112 | |
5.9% | - | |
4.5 | 2.5 | |
about 2 months ago | 6 days ago | |
Python | 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.
descript-audio-codec
-
Show HN: Sonauto – a more controllable AI music creator
Hey HN,
My cofounder (four months ago, classmate) and I trained an AI music generation model and after a month of testing we're launching 1.0 today. Ours is interesting because it's a latent diffusion model instead of a language model, which makes it more controllable: https://sonauto.ai/
Others do music generation by training a Vector Quantized Variational Autoencoder like Descript Audio Codec (https://github.com/descriptinc/descript-audio-codec) to turn music into tokens, then training an LLM on those tokens. Instead, we ripped the tokenization part off and replaced it with a normal variational autoencoder bottleneck (along with some other important changes to enable insane compression ratios). This gave us a nice, normally distributed latent space on which to train a diffusion transformer (like Sora). Our diffusion model is also particularly interesting because it is the first audio diffusion model to generate coherent lyrics!
We like diffusion models for music generation because they have some interesting properties that make controlling them easier (so you can make your own music instead of just taking what the machine gives you). For example, we have a rhythm control mode where you can upload your own percussion line or set a BPM. Very soon you'll also be able to generate proper variations of an uploaded or previously generated song (e.g., you could even sing into Voice Memos for a minute and upload that!). @Musicians of HN, try uploading your songs and using Rhythm Control/let us know what you think! Our goal is to enable more of you, not replace you.
For example, we turned this drum line (https://sonauto.ai/songs/uoTKycBghUBv7wA2YfNz) into this full song (https://sonauto.ai/songs/KSK7WM1PJuz1euhq6lS7 skip to 1:05 if inpatient) or this other song I like better (https://sonauto.ai/songs/qkn3KYv0ICT9kjWTmins we accidentally compressed it with AAC instead of Opus which hurt quality, though)
We also like diffusion models because while they're expensive to train, they're cheap to serve. We built our own efficient inference infrastructure instead of using those expensive inference as a service startups that are all the rage. That's why we're making generations on our site FREE and UNLIMITED for as long as possible.
We'd love to answer your questions. Let us know what you think of our first model! https://sonauto.ai/
-
TSAC: Low Bitrate Audio Compression
Another useful model to compare to would be DAC https://github.com/descriptinc/descript-audio-codec
This is the codec that TSAC extended, so it could be a nice comparison to see. I'd also echo Vocos (from sibling comment), it operates on the same Encodec tokens but generally has better reconstruction quality.
pytorch-CycleGAN-and-pix2pix
-
List of AI-Models
Click to Learn more...
- I want an A.I. to learn my art style so I can keep making art in my art style despite not having the time to do it.
-
I'm looking for an AI Art generator from images
pix2pix (https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix) - This is a PyTorch implementation of the pix2pix algorithm for image-to-image translation. Given a set of images, the model can learn to generate a new image from a different domain that is similar to the input image.
-
Seamless textures with SD and PBR maps with a pix2pix cGAN
Using junyanz/pytorch-CycleGAN-and-pix2pix as a basis for pix2pix, I applied the same blending method to fix seams. It essentially takes an input image and generates an output. The results depend on the paired training data. In this case, each map (height, roughness, etc.) is a separate checkpoint and had to be trained on paired training data with the diffuse as the input and the respective map as the output.
- IA art
- Segmentation and clasification with UNET
-
Trying to understand PatchGAN discriminator
Code for https://arxiv.org/abs/1611.07004 found: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
-
I made a 3d topographic map based on my recent civ6 game
pix2pix algorithm is used for translating Civ6Maps to heightmaps. Synthesized terrain was rendered in blender.
-
This Wojak Does Not Exist
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
-
Training a neural net to generate Wojaks
I'm working on creating a face-to-wojak model using PyTorch CycleGan/Pix2Pix [0] and found some of my outputs to be outrageous yet somehow relatable. People are into it so thought I'd share on HN
[0] https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
What are some alternatives?
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
generative-inpainting-pytorch - A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
pytorch-grad-cam - Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Deep-Fakes
AnimeGAN - Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper
PaddleGAN - PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
Anime-face-generation-DCGAN-webapp - A port of my Anime face generation using Pytorch into a Webapp
DeepMosaics - Automatically remove the mosaics in images and videos, or add mosaics to them.
SimSwap - An arbitrary face-swapping framework on images and videos with one single trained model!
anycost-gan - [CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
CycleGAN - Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Im2Vec - [CVPR 2021 Oral] Im2Vec Synthesizing Vector Graphics without Vector Supervision