Making large AI models cheaper, faster and more accessible

Official implementation of VQ-Diffusion

A multi-voice TTS system trained with an emphasis on quality

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Finetuning SD in style.

Point cloud diffusion for 3D model synthesis

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

[ICCV 2023] A latent space for stochastic diffusion models

Audio generation using diffusion models, in PyTorch.

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

TextBox 2.0 is a text generation library with pre-trained language models

Model interpretability and understanding for PyTorch

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.

[CVPR 2023] MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Official implementation of Cold-Diffusion for different transformations in pytorch.

🖌 photorealistic drawings from simple sketches using NVIDIA's GauGAN

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

High-Resolution Image Synthesis with Latent Diffusion Models

Paint by Example: Exemplar-based Image Editing with Diffusion Models