🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

[ICLR 2025] Official code repository for "TULIP: Token-length Upgraded CLIP"

Sync and Async Object-oriented Python SDK for the 3x-ui API.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

Next generation frontend tooling. It's fast!

[CVPR2023] Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning (https://arxiv.org/abs/2212.04500)

[RAL 2022] Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving

[CVPR 2025] Multiple Object Tracking as ID Prediction

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

PuLID native implementation for ComfyUI

Active Learning in the era of Foundation Models

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment

Measures and metrics for image2image tasks. PyTorch.

Official PyTorch implementation of "Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization" (ECCV 2024)

CLIP+MLP Aesthetic Score Predictor

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.

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

[NeurIPS2023] DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models

[ICCV2023] DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models

The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)