CVPR2026 Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers

A unified framework for easy reinforcement learning in Flow-Matching models

[ICLR 2026] "Does FLUX Already Know How to Perform Physically Plausible Image Composition?" (Official Implementation)

[CVPR2026 🎉] Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.

FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity co…

Implementation of VLM4VLA

Streaming Flux editor: live camera→ editing every frames at interactive FPS based on FLUX.2-Klein-4B. Runs on a single H100 at 15+ FPS

The ultimate training toolkit for finetuning diffusion models

NanoBanana PPT Skills 基于 AI 自动生成高质量 PPT 图片和视频的强大工具，支持智能转场和交互式播放

Scalable group inference for generating high quality and diverse images with diffusion models.

[NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

[ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

[Tutorial] Few-Step Distillation for Text-to-Image Generation: A Practical Guide

Visual Generation Tuning

[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Official Implementation of "MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation"

[DEIMv2] Real Time Object Detection Meets DINOv3

聚宽网量化投资策略编写的学习文档

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3

Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

TradingAgents: Multi-Agents LLM Financial Trading Framework

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

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)

Implementation of MagViT2 Tokenizer in Pytorch

[ICCV 2025] Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics.