[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Fork of SageAttention for Windows wheels and easy installation

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

A minimalistic implementation of Robust Video Matting (RVM) and BRAIAI-RVMBG v1.4 in ComfyUI

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)

A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

[CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

[ECCV2024] Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization

[CVPR 2025 Highlight] Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

Some Comfyui custom nodes for wan2.1 VACE, attempt to implement VACE video generation/editing in a better way.

Twitter API Scraper | Without an API key | Twitter Internal API | Free | Twitter scraper | Twitter Bot

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

Lightweight nudity detection

A simple python script to detect nudity in images. Huggingface Model repo: https://huggingface.co/esvinj312/nudity-detection

A Neural Net for Nudity Detection. Classifier only.

A Python project which can detect gender and age using OpenCV of the person (face) in a picture or through webcam.

MiVOLO age & gender transformer neural network

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Call LLM and VLM in a simple way using the OpenAI API standard from ComfyUI