Zhuoran Zhao

lingbot-video. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

lingbot-world-v2. Infinite Worlds with Versatile Interactions

mira. Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

VisionReward. [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Gamma-World. Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

flash-attention-prebuild-wheels. Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

Rolling-Sink. Official implementation of "Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion"

OmniGameArena. OmniGameArena

JoyAI-Echo. JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

rcm. rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

videophy. Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics

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

One-Forcing. Official codebase for "One-Forcing: Towards Stable One-Step Autoregressive Video Generation"

awesome-diffusion-human-centric.

LongLive. Long Video Gen Infrastructure

FastGen. NVIDIA FastGen: Fast Generation from Diffusion Models

RAVEN. Implementation of our paper "RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO"

Prism. [ICML 2026] Official Implementation of Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

Flow-OPD. Official Repo of "Flow-OPD: On-Policy Distillation for Flow Matching Models"

Awesome-Relight. A curated list of relighting papers, datasets, benchmarks, demos, and tools.

UniVidX. [SIGGRAPH 2026 / TOG] Official code of the paper "UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors".

GeometryForcing. [ICLR26] Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

SesaHand. [ICLR 2026] SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment

DreamX-World. DreamX-World: A General-Purpose Interactive World Model

Causal-Forcing. [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

DreamWorld. DreamWorld: Unified World Modeling in Video Generation

ShotStream. [ECCV 2026] ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Ditto. [CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

VideoREPA. [NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

REPA. [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Infinite-Forcing. Infinite-Forcing: Towards Infinite-Long Video Generation

infinity-rope. [CVPR 2026] Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

CameraCtrl. Python

GrndCtrl.

UnifiedReward. Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex

Awesome-Human-Interaction-Motion-Generation. This repository collects papers on Human-Interaction-Motion-Generation applications. We will update new papers irregularly.

Awesome-RL-for-Video-Generation. A curated list of papers on reinforcement learning for video generation

Reward-Forcing. [CVPR 2026 Highlight] Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Astrolabe. Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Matrix-Game. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

solaris. The first multiplayer video world model in Minecraft

FastVideo. A unified inference and post-training framework for accelerated video generation.

worldfm. Python

LlamaGen. Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

AssetFormer. [ICLR'2026] AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

EasyCache. Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching

Bagel. Open-source unified multimodal model

Scale-RAE. Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Helios. Helios: Real Real-Time Long Video Generation Model

Self-Flow. [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

RelaxFlow. [ICML 2026 Spotlight] RelaxFlow: Text-Driven Amodal 3D Generation

TransNetV2. TransNet V2: Shot Boundary Detection Neural Network

figures4papers. My Python scripts to make high-quality figures for publications in top AI conferences and journals.

ChordEdit. [CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

MagicQuillV2. Official Implementations for Paper - MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues

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

SAEdit. The official implementation of the paper SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder

VIVA. Python

PosterOmni. [CVPR2026] PosterOmni: One model for poster creation—unifying local edits and global design for generalized multi-task image/poster-to-poster generation.

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Being-H. Being-H is BeingBeyond's family of human-centric embodied foundation models.

lingbot-vla. A Pragmatic VLA Foundation Model

UnityVideo. [CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

ORION. [RA-L 2026] ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation

PerpetualWonder. Python

LaGoVAD-PreVAD. [ICLR 26] This repository contains the code and dataset for our paper: Language-guided Open-world Video Anomaly Detection under Weak Supervision (https://arxiv.org/abs/2503.13160)

motion-edit. Official Repository of paper: "MotionEdit: Benchmarking and Learning Motion-Centric Image Editing"

coarse2real. C2R: Coarse-to-Real

EgoIntention. [ICCV 2025][EgoIntention] Visual Intention Grounding for Egocentric Assistants

VideoAlign. [NeurIPS 2025] Improving Video Generation with Human Feedback

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

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

Being-H0. Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos (ICML 2026)

IdentityStory. [AAAI 2026] Offical implementation of the paper "IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation".

lingbot-world. Advancing Open-source World Models

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

RealViformer. [ECCV2024] The Official Code for "RealViformer: Investigating Attention for Real-World Video Super-Resolution"

SeedVR. Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

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

dynvfx. [SIGGRAPH Asia 2025] Official Pytorch Implementation for "DynVFX: Augmenting Real Videos with Dynamic Content"

GameFactory. [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

LTX-Video. Official repository for LTX-Video

TokenFlow. Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

instruct-video-to-video. Python

InsViE. Official PyTorch implementation of paper “InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction”

Context_Aware_Navigation. [CoRL 2023] Context-Aware Deep Reinforcement Learning for Autonomous Robotic Navigation in Unknown Area - - Public code and model

BiCo. [CVPR 2026 Highlight] Official implementation of BiCo: Composing Concepts from Images and Videos via Concept-prompt Binding

BUAA_OS_2020Spring. C

DUSA. [ACM MM 2023] Official implementation of DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception

C-Instructor. [ECCV 2024] Official implementation of C-Instructor: Controllable Navigation Instruction Generation with Chain of Thought Prompting

DAM-VSR. [ACM SIGGRAPH 2025] DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution

HoloCine. [CVPR 2026 Highlight] Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

LongCat-Video. Python

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

pyheal. Pure Python implementation of Telea FMM inpainting

sam3. The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

AnchorDS. [AAAI 2026] AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation

pix2video. Code for the paper "Pix2Video: Video Editing using Image Diffusion"

VEGGIE-VidEdit. [ICCV2025] VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

yarn. YaRN: Efficient Context Window Extension of Large Language Models

FlashVSR. [CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

poisson-image-editing. Jupyter Notebook

poisson-image-editing. Poisson image editing for seamless cloning and other operations

pytorch-poisson-image-editing. Fast Python implementations of Poisson image editing, using Pytorch and NumPy.

Poisson-Image-Editing. Implementation of Poisson Image Editing (Patrick Perez et al. Microsoft Research UK)

mixture-of-diffusers. Mixture of Diffusers for scene composition and high resolution image generation

tiled-diffusion. Official implementation of "Tiled Diffusion" [CVPR 2025]

StyleID. [CVPR 2024 Highlight] Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

CogniPlan. [CoRL 2025] CogniPlan: Uncertainty-Guided Path Planning with Conditional Generative Layout Prediction - Public code and model

Rex-Thinker. [ICLR-2026] Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning

Neural-Preset. an unofficial implementation of the paper "Neural Preset for Color Style Transfer" (CVPR 2023), including ~300 LUT files

NeuralPreset. AI-Generated Presets for Faithful 4K Color Style Transfer in Real Time [CVPR 2023]

FouriScale. Official implementation of FouriScale (ECCV2024)

MoGe. [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

GEN3C. [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

diffusion-renderer. [CVPR'25 Oral] Official implementation for "DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models"

DemoFusion. Let us democratise high-resolution generation! (CVPR 2024)

PSAlign. Official Implementation of "PSAlign: Personalized Safety Alignment for Text-to-Image Diffusion Models"

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

MasaCtrl. [ICCV 2023] Consistent Image Synthesis and Editing

stable-flow. Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

FlowEdit. Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

uspace. An official pytorch implementation of AAAI 2024 paper "Latent Space Editing in Transformer-based Flow Matching"

pytorch_wavelets. Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

FlowMo. Official PyTorch implementation of FlowMo.

Tune-A-Video. [ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

RealCam-I2V. Python

Video-P2P. Video-P2P: Video Editing with Cross-attention Control

RealCam-Vid. open-sourced video dataset with dynamic scenes and camera movements annotation

UltraVideo. [[NeurIPS 2025] UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

awesome-diffusion-v2v. Awesome diffusion Video-to-Video (V2V). A collection of paper on diffusion model-based video editing, aka. video-to-video (V2V) translation. And a video editing benchmark code.

FDS. Official code of FDS (CVPR 2025)

CineScale. Code for CineScale, higher-resolution video generation based on Wan

AniLines-Anime-Lineart-Extractor. Extracting lineart from anime images and videos.

jonbarron.github.io. HTML

Deep-Sketch-Vectorization. Python

Awesome-Animation-Research. Papers, datasets, and resources related to 2D cartoon video research. Contributions welcome.

SakugaDataset. Official Repository for Sakuga-42M Dataset

LongAnimation. Python

Go-with-the-Flow. The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

LightGlue. LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

InteractVLM. [CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

VHAP. A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.

MaskGIT-pytorch. Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)

magvit. Official JAX implementation of MAGVIT: Masked Generative Video Transformer

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

DiffSynth-Studio. Enjoy the magic of Diffusion models!

adobe-scripting. A guide for learning how to write scripts for use in Adobe Illustrator

Score-Entropy-Discrete-Diffusion. [ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

SketchyScene. [ECCV 2018] SketchyScene: Richly-Annotated Scene Sketches

FUDOKI. [NeurIPS 2025 Spotlight] FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

DLLM-Survey. [Arxiv] Discrete Diffusion in Large Language and Multimodal Models: A Survey

Awesome-Controllable-Video-Generation. [ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

AnimateDiff. Official implementation of AnimateDiff.

unidisc. UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, and inpainting.

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

DreamRelation. [CVPR 2025] DreamRelation: Bridging Customization and Relation Generation

mdlm. [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

FoundHand. Python

david. Official Repository for ICCV 2025 paper DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models

clean-fid. PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

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

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

X-Dyna. [CVPR 2025 Highlight] X-Dyna: Expressive Dynamic Human Image Animation

HaWoR. HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos

sd3.5. Python

Dual-Diffusion. Code for D-DiT

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

WiLoR. WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

Image-Generation-CoT. [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

FollowYourPose. [AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

sd-webui-controlnet. WebUI extension for ControlNet

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

InkLayer. Official Implementation of "Instance Segmentation of Scene Sketches Using Natural Image Priors" (SIGGRAPH 2025)

Anime2Sketch. A sketch extractor for anime/illustration.

Muddit. [ICLR 2026] Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.

XDoG-PyTorch. PyTorch Implementation of XDoG & DoG

xdog-sketch. Non-photorealistic, sketch style rendering in the browser with deeplearn.js + React 🎨

SceneSketch. Python

MagicQuill. [CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

MagicTailor. [IJCAI 2025 (Oral)] Offical implementation of the paper "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models".

AniDoc. [CVPR'25] Official Implementations for Paper - AniDoc: Animation Creation Made Easier

MMaDA. MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

cs-paper-checklist. A final sanity checklist to help your CS paper get accepted, not desk rejected.

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

SketchVideo. Python

flux. Official inference repo for FLUX.1 models

videocomposer. Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability

PyTorch-FID-score. FID is a measure of similarity between two datasets of images and considered to be the better evaluation metrics compared to IS, since the data distribution can be calculated from real samples and generated samples.

Empirical-Study-of-GPT-4o-Image-Gen. An Empirical Study of GPT-4o Image Generation Capabilities

HandSynthesis. [CVPR 2025] Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation

Awesome-RAG-Vision. Awesome-RAG-Vision: a curated list of advanced retrieval augmented generation (RAG) for Computer Vision

torch-fidelity. High-fidelity performance metrics for generative models in PyTorch