#
Starred repositories
你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
PyTorch code for our paper "Image Super-Resolution with Text Prompt Diffusion"
[CVPR 2024] CoSeR: Bridging Image and Language for Cognitive Super-Resolution
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
[ECCV2024] Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution
T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!
Official Repository of the paper "Trajectory Consistency Distillation"
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
[AAAI 2025] Official codes of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".
[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model
Official PyTorch implementation of ECCV 2024 Paper: ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.
A collection of awesome-lists for AI, creativity and art. AI、创意和艺术领域的精选合集。https://latentbox.com
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
Deploy high-performance AI models and inference pipelines on FastAPI with built-in batching, streaming and more.
⛓️ Serving LangChain LLM apps and agents automagically with FastApi. LLMops
Run PyTorch LLMs locally on servers, desktop and mobile
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
Unified framework for building enterprise RAG pipelines with small, specialized models
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Efficient Retrieval Augmentation and Generation Framework
A vector search SQLite extension that runs anywhere!