Jianzong Wu

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

UniCharacter. An official implementation of Towards Customized Multimodal Role-Play.

LLaDA2.0-Uni. LLaDA2.0-Uni: Understanding and Generation the World.

Kiwi-Edit. A unified and fully open-source framework for instruction-guided and reference-guided video editing using natural language.

MOVA. MOVA: Towards Scalable and Synchronized Video–Audio Generation

LTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Sora2-mini. UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

HunyuanVideo-1.5. HunyuanVideo-1.5: A leading lightweight video generation model

molmo2. Code for the Molmo2 Vision-Language Model

UniVideo. [ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos

Does-Hearing-Help-Seeing. Python

GPT-Image-Edit. GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

BLIP3o. Official implementation of BLIP3o-Series

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

emma. Official repo for paper "EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture."

DraCo. Offical Repository for Paper: DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

tuna.

AIA. Python

Step1X-Edit. A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Mirage. [CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

Monet. [CVPR 2026] Official codes of "Monet: Reasoning in Latent Visual Space Beyond Image and Language"

Emu3.5. Native Multimodal Models are World Learners

UniLIP. [ICLR 2026 🔥 ] Official implementation of "UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing"

Qwen3-Omni. Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

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

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

Qwen2-Audio. The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Qwen2.5-Omni. Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

UniVerse-1-code. The official UniVerse-1 code.

Koala-36M. Official implementation of the paper "Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content".

Waver. Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

UniCTokens. A framework for unified personalized model, achieving mutual enhancement between personalized understanding and generation. Demonstrating the potential of cross-task information transfer in personalized scenario, paving the way for the development of general unified models.

UniPic. Open-source SOTA multi-image editing model

memfof. [ICCV'2025 Highlight] MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation

thinking-with-generated-images. Doodling our way to AGI ✏️ 🖼️ 🧠

tarsier. Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

X-Omni. Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

ARC-Hunyuan-Video-7B. Structured Video Comprehension of Real-World Shorts

VideoLLaMA2. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Keye. Python

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

Ctrl-Crash. Official PyTorch Implementation of Ctrl-Crash 💥

AudioLDM2. Text-to-Audio/Music Generation

Index-anisora. Python

star-vector. StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

CoDi. CoDi:Subject-Consistent and Pose-Diverse Text-to-Image Generation

Lumos. [ICLR 2026] Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

Ovis-U1. An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

attention-interpolation-diffusion. [NeurIPS 2024] Official Implementation of Attention Interpolation of Text-to-Image Diffusion

ControlNet. Generate videos that interpolate between two given images

ShareGPT-4o-Image. Python

VMoBA. Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"

OmniCorpus. [ICLR 2025 Spotlight] OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

TPDM. Implementation of "Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation" [CVPR 2025]

JavisDiT. [ICLR 2026] Official implementation of JavisDiT and JavisDiT++ series.

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

Bagel. Open-source unified multimodal model

PSDiffusion.

TeaCache. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

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

Sparse-VideoGen. [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

DiTFastAttn. Jupyter Notebook

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

SpargeAttn. [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

rlhf-flow-diffusion. Reinforcement Learning from Human Feedback for Flow-Based Diffusion Models

ddpo-pytorch. DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support

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

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

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

MoBA. MoBA: Mixture of Block Attention for Long-Context LLMs

Awesome-Visual-Autoregressive-Model. Latest Advances on Autoregressive Visual Models.📖

hart. HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

NATTEN. Fast Multi-dimensional Sparse Attention

DeepSeek-V3. Python

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

CLEAR. [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".

LinFusion. Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"

VSSD. [ICCV2025] Introduce Mamba2 to Vision.

tread. Python

Vim. [ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Sa2VA. Official Repo For Pixel-LLM Codebase: Sa2VA (PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

LTX-Video. Official repository for LTX-Video

mamba. Mamba SSM architecture

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

U-DiT. [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"

SakugaDataset. Official Repository for Sakuga-42M Dataset

anomaly-seg. The Combined Anomalous Object Segmentation (CAOS) Benchmark

dataset-api. The ApolloScape Open Dataset for Autonomous Driving and its Application.

diamond. DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

VBench. [CVPR2024 Highlight] VBench - We Evaluate Video Generation

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

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

GameGen-X.

Playable-Game-Generation. An open-source lightweight game generation paradigm. It includes everything from data processing to model architecture design and playability-based evaluation methods. The game runs at 20 FPS on a single consumer-grade graphics card (RTX-2060) while maintaining high playability.

ditflow. Official PyTorch implementation - Video Motion Transfer with Diffusion Transformers

DiffSensei. Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

physgen. PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)

Emu. Emu Series: Generative Multimodal Models from BAAI

SEED-X. Multimodal Models in Real World

Show-o. [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

CSGO. CSGO: Content-Style Composition in Text-to-Image Generation 🔥

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

X-Pose. [ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

InstantID. Python

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

insightface. State-of-the-art 2D and 3D Face Analysis Project

awesome-comics-understanding. The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

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

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

InternVL. [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

UniPortrait. [ICCV2025] UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization

VideoTetris. [NeurIPS 2024] VideoTetris: Towards Compositional Text-To-Video Generation

direct_a_video. Python

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

SEED-Story. SEED-Story: Multimodal Long Story Generation with Large Language Model

ReVersion. [SIGGRAPH Asia 2024] ReVersion: Diffusion-Based Relation Inversion from Images

Analogist. Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model (SIGGRAPH 2024)

MS-Diffusion. [ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

ai-comic-factory. Generate comic panels using a LLM + SDXL. Powered by Hugging Face 🤗

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

StoryGen. [CVPR 2024] Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

TheaterGen. TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation

AutoStudio. [CVPRW 2026] AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation

ToonCrafter. [SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

MG-LLaVA. Official repository for paper MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning(https://arxiv.org/abs/2406.17770).

MotionBooth. [NeurIPS 2024 Spotlight] The official implement of research paper "MotionBooth: Motion-Aware Customized Text-to-Video Generation"

mangadex. A python wrapper for the mangadex API V5. Work in progress

magi. Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. Order panels. Cluster characters. Match texts to their speakers. Perform OCR.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

manga109api. Simple python API to read annotation data of Manga109

Omost. Your image is almost there!

style-aligned. Official code for "Style Aligned Image Generation via Shared Attention"

cross-image-attention. Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

InST. Official implementation of the paper “Inversion-Based Style Transfer with Diffusion Models” (CVPR 2023)

FreeStyle. FreeStyle : Free Lunch for Text-guided Style Transfer using Diffusion Models

CameraCtrl. Python

MotionEditor. [CVPR2024] MotionEditor is the first diffusion-based model capable of video motion editing.

Moore-AnimateAnyone. Character Animation (AnimateAnyone, Face Reenactment)

champ. [ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

MagicDance. [ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

DreamPose. Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

DisCo. [CVPR2024] DisCo: Referring Human Dance Generation in Real World

FIFO-Diffusion_public. Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024)

handy_voting. handy tools for user study

AnimateDiff. Official implementation of AnimateDiff.

FreeCustom. [CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Panda-70M. [CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

VideoBooth. [CVPR2024] VideoBooth: Diffusion-based Video Generation with Image Prompts

VGen. Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

FreeNoise. [ICLR 2024] Code for FreeNoise based on VideoCrafter

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

SEINE. [ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

StreamingT2V. [CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

DenseDiffusion. Official Pytorch Implementation of DenseDiffusion (ICCV 2023)

StableCascade. Official Code for Stable Cascade

ReferFormer. [CVPR2022] Official Implementation of ReferFormer

ovsam. [ECCV 2024] The official code of paper "Open-Vocabulary SAM".

OMG-Seg. Official Repo For OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

TrailBlazer. [SIGGRAPH Asia 2024] TrailBlazer: Trajectory Control for Diffusion-Based Video Generation

MotionCtrl. Official Code for MotionCtrl [SIGGRAPH 2024]

PhotoMaker. PhotoMaker [CVPR 2024]

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

Peekaboo. Interactive Video Generation via Masked-Diffusion

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

modelscope. ModelScope: bring the notion of Model-as-a-Service to life.

LaVie. [IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

Gen-L-Video. The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

BoxDiff. [ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

freecontrol. Official implementation of CVPR 2024 paper: "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition"

tianxingwu.github.io. My homepage https://tianxingwu.github.io

FreeInit. [ECCV 2024] FreeInit: Bridging Initialization Gap in Video Diffusion Models

ElasticDiffusion-official. The official Pytorch Implementation for ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation (CVPR 2024)

MultiDiffusion. Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

VideoDirectorGPT. official implementation of VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning (COLM 2024)

Paint-by-Example. Paint by Example: Exemplar-based Image Editing with Diffusion Models

LLM-groundedDiffusion. LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)

LLM-groundedVideoDiffusion. [ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper

Mix-of-Show. NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

AutoStory. [IJCV'24] AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

UDiffText. [ECCV 2024] Official repo for UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

generative-models. Generative Models by Stability AI

acad-homepage.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

shields. Concise, consistent, and legible badges in SVG and raster format

PixArt-alpha. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

ReLA. [CVPR 2023 Highlight & IJCV 2026] GRES: Generalized Referring Expression Segmentation

ContextDET. Contextual Object Detection with Multimodal Large Language Models

groundingLMM. [CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

lang-segment-anything. SAM with text prompt

instruct-pix2pix. Python

dst-det. [TCSVT] state-of-the-art open vocabulary detector on COCO/LVIS/V3Det

Mini-DALLE3. Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models

LISA. Project Page for "LISA: Reasoning Segmentation via Large Language Model"

ODISE. Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

ProPainter. [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

index-X. 禁书目录X系列，不一样的阅读体验！

InstructDiffusion. PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.