yigityu's starred repositories
audiocraft
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.
bark-with-voice-clone
🔊 Text-prompted Generative Audio Model - With the ability to clone voices
DeepFilterNet
Noise supression using deep filtering
StableDiffusion-CheatSheet
A list of StableDiffusion styles and some notes for offline use. Pure HTML, CSS and a bit of JS.
ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
soundstorm-pytorch
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
Prompt-Free-Diffusion
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024
bark-voice-cloning-HuBERT-quantizer
The code for the bark-voicecloning model. Training and inference.
StyleDrop-PyTorch
Unoffical implement for [StyleDrop](https://arxiv.org/abs/2306.00983)
Prompt-Diffusion
Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"
AnimeInbet
Code and data for ICCV23 work "Deep Geometrized Cartoon Line Inbetweening"
SoundStorm
The reproduced code for Google's SoundStorm
Whispering-LLaMA
EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction
RAVE-Latent-Diffusion
Generate new latent codes for RAVE with Denoising Diffusion models.
react-native-unity
React Native package to use Unity as library with RN app
Kandinsky-2-textual-inversion
Kandinsky 2 — multilingual text2image latent diffusion model
com.unity.addressables
Addressables extended with the ability to build multiple catalogs, ideal for traditional DLC purposes.
react-native-unity2
Embed Unity content in your React Native app!
Philia-GUI
An easy to use imageboard scraper.
bark-with-voice-clone
🔊 Text-prompted Generative Audio Model - With the ability to clone voices
com.unity.addressables
[Mirrored from UPM, without any changes. Maintained by Needle. Not affiliated with Unity Technologies.] 📦 The Addressable Asset System allows the developer to ask for an asset via its address. Once an asset (e.g. a prefab) is marked "addressable", it generates an address which can be called from anywhere. Wherever the asset resides (local or remote), the system will locate it and its dependencies, then return it.Use Window->Asset Management->Addressables to begin working with the system.Addressables use asynchronous loading to support loading from any location with any collection of dependencies. Whether you have been using direct references, traditional asset bundles, or Resource folders, addressables provide a simpler way to make your game more dynamic. Addressables simultaneously opens up the world of asset bundles while managing all the complexity.For usage samples, see github.com/Unity-Technologies/Addressables-Sample