Penalty_kl

Hint2Gen. Source code for Hint2Gen

MegaStyle. MegaStyle, 面向一致性与多样性的可扩展风格数据生成框架

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

TEMF. Source code for TEMF

live-swe-agent. Live-SWE-agent: live, runtime self-evolving software engineering agent

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

SWE-bench. SWE-bench: Can Language Models Resolve Real-world Github Issues?

kandinsky-5. Kandinsky 5.0: A family of diffusion models for Video & Image generation

MemFlow. Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

DreamMask. Source code for SIGGRAPH25 DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data

Concerto. [NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Paper2Video. Automatic Video Generation from Scientific Papers

MCDL. Code for MCDL

VideoAnydoor. [SIGGRAGH'25] Official repository of VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

yuanpengtu.

PlayerOne. PlayerOne: Egocentric World Simulator

Awesome-World-Model. Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

egomono4d. Official Reporsitory of "EgoMono4D: Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos"

Geo4D. [ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

FramePack. Lets make video diffusion practical!

Pusa-VidGen. Pusa: Thousands Timesteps Video Diffusion Model

EgoBody3M. EgoBody3M Egocentric Body Tracking on a VR Headset using a Diverse Dataset

EgoExo-Fitness. (ECCV 2024) Official repository of paper "EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding"

UnrealEgo. The official implementation of our ECCV 2022 paper, "UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture".

hot3d. HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos, CVPR 2025

egoallo. Estimating Body and Hand Motion in an Ego-sensed World

VideoScene. [CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

egowholemocap. implementation of paper: Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement

EgoHMR. PyTorch code for EgoHMR (ICCV 2023): Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views

eqvae. [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.

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.

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

awesome-egocentric-vision. A curated list of egocentric (first-person) vision and related area resources

HSR. HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024)

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

GoT. Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"

VideoGrain. [ICLR 2025] VideoGrain: This repo is the official implementation of "VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing"

Tora. [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation

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

EgoLife. [CVPR 2025] EgoLife: Towards Egocentric Life Assistant

SmartEraser. [CVPR 2025] Official implementation of the paper "SmartEraser: Remove Anything from Images using Masked-Region Guidance".

Cinemo. [CVPR 2025] Consistent and Controllable Image Animation with Motion Diffusion Models

MatAnyone. [CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

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

Detect-AnyShadow. Official PyTorch implementation for TCSVT 23 "Detect Any Shadow: Segment Anything for Video Shadow Detection"

SMPLer-X. [NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

SkyReels-V1. SkyReels V1: The first and most advanced open-source human-centric video foundation model

SkyReels-A1. SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

MoneyPrinterV2. Automate the process of making money online.

Step-Video-T2V. Python

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

Ego-Exo4D-docs. JavaScript

defisheye. Fast Corrects for fisheye distortion in an image.

VARGPT. VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

NOVA. [ICLR 2025] Autoregressive Video Generation without Vector Quantization

Lumina-Video. Python

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

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

egopet. Official implementation of the paper "EgoPet: Egomotion and Interaction Data from an Animal's Perspective".

DiffuEraser. DiffuEraser is a diffusion model for video inpainting, which performs great content completeness and temporal consistency while maintaining acceptable efficiency.

id-pose. ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models

you2me. Inferring Body Pose in Egocentric Video via First and Second Person Interactions

VidGen. Python

Orient-Anything. Orient Anything, ICML 2025

causalfusion. Python

LuminaBrush. Illumination Drawing Tools for Text-to-Image Diffusion Models

nymeria_dataset. Official repo for Nymeria and NymeriaPlus datasets.

OminiControl. [ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

DiTCtrl. [CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

VideoVAEPlus. [ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

awesome-brain-decoding. A curated list of awesome papers on visual reconstructions from brain activity.

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

Kandinsky-4. Text and image to video generation: Kandinsky 4.0 (2024)

finetrainers. Scalable and memory-optimized training of diffusion models

CAR. CAR: Controllable AutoRegressive Modeling for Visual Generation

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

MimicMotion. High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

echomimic_v2. [CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

In-Context-LoRA. Official repository of In-Context LoRA for Diffusion Transformers

IC-Light. More relighting!

tao. Code for downloading and using the TAO dataset: http://taodataset.org/

FluxKits. Python

LTX-Video. Official repository for LTX-Video

DINO-X-API. DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

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

co-tracker. CoTracker is a model for tracking any point (pixel) on a video.

eye_for_an_eye. Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models

ViViD. ViViD: Video Virtual Try-on using Diffusion Models

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

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

Lotus. Official implementation of "Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction"

Large-Scale-Medical. [TPAMI 2026] Large-Scale 3D Medical Image Pre-training with Geometric Context Priors

SVD_Xtend. Stable Video Diffusion Training Code and Extensions.

Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

MusePose. MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

LM_Transformers_BlockMerge. Image Diffusion block merging technique applied to transformers based Language Models.

FLUX-Controlnet-Inpainting. Python

diffusion-e2e-ft. [WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

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

RealisDance. The official implementation of RealisDance

DOVER. [ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.

LiteGen. A light-weight and high-efficient training framework for accelerating diffusion tasks.

Arc2Face. [ECCV 2024 Oral 🔥] Arc2Face: A Foundation Model for ID-Consistent Human Faces ------------------------ [ICCVW 2025] ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion

RegionDrag. [ECCV2024] RegionDrag: Fast Region-Based Image Editing with Diffusion Models

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

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.

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

Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

RADIO. Official repository for "AM-RADIO: Reduce All Domains Into One"

MimicBrush. Official implementations for paper: Zero-shot Image Editing with Reference Imitation

comfyui-inpaint-nodes. Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.

x-flux. Python

xDiT. xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

ml-mgie. Python

SmartEdit. Official code of SmartEdit [CVPR-2024 Highlight]

ControlNet-XS. Python

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

AnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

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

flux. Official inference repo for FLUX.1 models

stable-fast-3d. SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

SpaTracker. [CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ReVideo. NeurIPS 2024

ControlNetPlus. ControlNet++: All-in-one ControlNet for image generations and editing!

SPRIGHT. [ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"

LayerDiffuse. Transparent Image Layer Diffusion using Latent Transparency

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

ControlNeXt. Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

sd-scripts. Python

LivePortrait. Bring portraits to life!

awesome-virtual-try-on. A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.

LSFA. Source code for Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection (ECCV 2024)

cambrian. Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2026-ECCV2024-AIGC. A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC

Vript. Python

Mira. Python

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

LLM101n. LLM101n: Let's build a Storyteller

prismatic-vlms. A flexible and efficient codebase for training visually-conditioned language models (VLMs)

OpenCLAY. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

ImprovedNAT. A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"

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

hallo. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

ColossalAI. Making large AI models cheaper, faster and more accessible

Depth-Anything-V2. [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

learning_research. 本人的科研经验

UniAnimate. Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

3DitScene. [ICLR 2025] 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

tapnet. Tracking Any Point (TAP)

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

Omost. Your image is almost there!

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

tc4d. TC4D: Trajectory-Conditioned Text-to-4D Generation

pykan. Kolmogorov Arnold Networks

Awesome-Diffusion-Model-Based-Image-Editing-Methods. Diffusion Model-Based Image Editing: A Survey (TPAMI 2025)

MotionInversion. [SIGGRAPH 2025] Official implementation of 'Motion Inversion For Video Customization'

co3d. Tooling for the Common Objects In 3D dataset.

VSPW-dataset-download. Python

DepthFlow. 🌊 Images to 3D parallax videos

llama3. The official Meta Llama 3 GitHub site

motionshop. Project page of replacing the human motion in the video with a virtual 3D human

FlashFace. Python

flownet2-pytorch. Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

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!

BFTT3D. Python

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

AniPortrait. AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

GRM. Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

semantic-draw. Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

grok-1. Grok open release

mvsplat. 🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

Pointcept. Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

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

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

FollowYourClick. [AAAI 2025] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"

VidProM. [NeurIPS 2024] VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

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

ViewDiff. ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

awesome-3d-diffusion. A collection of papers on diffusion models for 3D generation.

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

imaginAIry. Pythonic AI generation of images and videos

res-adapter. [AAAI 2025] Official codes of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".

onediff. OneDiff: An out-of-the-box acceleration library for diffusion models.

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

EMO. Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Latte. [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.

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

DiS. Scalable Diffusion Models with State Space Backbone

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

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

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

gemma_pytorch. The official PyTorch implementation of Google's Gemma models

DiffiT. [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation