Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944

Official implementation of EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]

Contexts Optical Compression

Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Wan2.2-Lightning: Speed up wan2.2 model with distillation

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

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

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、传统深度学习、自动驾驶、AI Agent、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

📚 AIGC 求职面经、必备基础知识、提示词工程、ChatGPT、Stable Diffusion、Prompt、Embedding、Fintune 等 AIGC 求职你所需要知道的一切~

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Light Video Generation Inference Framework

Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]

A pipeline parallel training script for diffusion models.

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Wan: Open and Advanced Large-Scale Video Generative Models

[Siggraph2025] The official code of the paper "ColorSurge: Bringing Vibrancy and Efficiency to Automatic Video Colorization via Dual-Branch Fusion"

SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation. IEEE TIP, 2023

Official Implementation of VideoDPO

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" [TMLR 2024]

Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library