Official PyTorch implementation - Video Motion Transfer with Diffusion Transformers

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing

Hackable implementation & tutorials for diffusion models 🦖

The ultimate training toolkit for finetuning diffusion models

[NIPS2025] RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

This is a repository to collect training-free algorithms for visual generation and manipulation

Implementation of STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

MotionStream: Real-Time Video Generation with Interactive Motion Controls

A collection of awesome text-to-image generation studies.

Training-Free Text-Guided Image Editing Using Visual Autoregressive Model

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

[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)

This repository serves as a record of the latest advancements in image and video generation and editing tasks based on the DiT architecture, including related papers, products, blogs, and more. If …

VideoCoF: Unified Video Editing with Temporal Reasoner

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

[ICCV 2025] FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

[CVPR 2025 Oral] Alias-free Latent Diffusion Models (official implementation)

Social media (Weibo) comments analyzing toolbox in Chinese 微博评论分析工具, 实现功能: 1.微博评论数据爬取; 2.分词与关键词提取; 3.词云与词频统计; 4.情感分析; 5.主题聚类

Wechat Chat History Exporter 微信聊天记录导出备份程序

Matlab implementation of BFCTN for HSI-MSI image fusion.

MATLAB implementation of BRFCTN for visual data denoising

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Implementation of the TPAMI paper {A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring, DOI: 10.1109/TPAMI.2025.3545605}

Cascade-Transform-based Tensor Nuclear Norm for Hyperspectral Image Super-Resolution

[CVPR 2025] Self-Learning Hyperspectral and Multispectral Image Fusion via Adaptive Residual Guided Subspace Diffusion Model