Opinionated and flexible ESLint shareable config by FANS

[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

Efficient optimizers

NviWatch: A blazingly fast rust based TUI for managing and monitoring NVIDIA GPU processes

Official inference repo for FLUX.1 models

The fastest way to create an HTML app

ControlNet++: All-in-one ControlNet for image generations and editing!

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

Stable Diffusion inference benchmarks

An extremely fast Python package and project manager, written in Rust.

PhotoMaker [CVPR 2024]

🛋 The AI and Generative Art platform for everyone

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Put Your Face Everywhere in Seconds.

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…

a state-of-the-art-level open visual language model | 多模态预训练模型

CodeImprover helps you improve, fix and find bugs in your code using GPT-4

[ICLR 2024] Code for FreeNoise based on VideoCrafter

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

🎦 Video comparison player for Mac and Windows, built using Electron

CoTracker is a model for tracking any point (pixel) on a video.

🎥 Python and OpenCV-based scene cut/transition detection program & library.

The Prodigy optimizer and its variants for training neural networks.

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention