Stars
A python library for self-supervised learning on images.
Piece it Together: Part-Based Concepting with IP-Priors
Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]
Official Implementation for "InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention"
Official implementation for "pOps: Photo-Inspired Diffusion Operators"
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
Official Implementation for "MyVLM: Personalizing VLMs for User-Specific Queries" (ECCV 2024)
Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"
Refine high-quality datasets and visual AI models
Official Implementation for "A Neural Space-Time Representation for Text-to-Image Personalization" (SIGGRAPH Asia 2023)
Official Implementation for "TEXTure: Text-Guided Texturing of 3D Shapes"
Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)
Official Implementation for "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures"
An open source implementation of CLIP.
Synthetic Faces High Quality (SFHQ) Dataset. 425,000 curated 1024x1024 synthetic face images
A latent text-to-image diffusion model
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing d…
Official implementation of Diffusion Autoencoders
[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" (AIM ECCVW 2022) https://arxiv.org/abs/2201.13433
stylegan3 encoder for image inversion