LPIPS metric. pip install lpips

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Stable Diffusion web UI

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

Real-time and accurate open-vocabulary end-to-end object detection

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-…

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Let us control diffusion models!

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

PyTorch code and models for the DINOv2 self-supervised learning method.

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Adapting Segment Anything Model for Medical Image Segmentation

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

We write your reusable computer vision tools. 💜

Segment Anything in High Quality [NeurIPS 2023]

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Inpaint anything using Segment Anything and inpainting models.

A library for efficient similarity search and clustering of dense vectors.

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"