✨ 望图 PixelFree 美颜SDK - 全平台美颜特效引擎（iOS/Android/harmonyOS/windows/macOS/linux）| 直播/短视频/相机/照片处理 | 高性能+轻量级

Real-time image filter engine based on GPU

This Repo. is used for our ACM MM2023 paper: Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

The official implementation of StereoPilot

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.

This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Taming large-scale few-step training with self-adversarial flows! 👏🏻

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

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

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…

Pytorch implementation of MeanFlow on ImageNet and CIFAR10

[NeurIPS 2025] MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

[CVPR 2024] Official implementation, Inversion-Free Image Editing with Natural Language"

unofficial Split Mean Flow Implementation from bytedance

🎁 6,500,000+ Unsplash images made available for research and machine learning

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[ICCV 2025] DiffDoctor: Diagnosing Image Diffusion Models Before Treating

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Fine-Grained GRPO for Precise Preference Alignment in Flow Models

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

Official Code and Dataset repository of Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures

Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.