Skip to content

@TencentARC ARC Lab, Tencent PCG

Change the repository type filter

All

    Repositories list

    77 repositories

    • TimeLens

      Public
      TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
      Python
      •
      Other
      •1•30•0•0•Updated Dec 17, 2025Dec 17, 2025

    • ColorFlow

      Public
      The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色
      computer-visionimage-colorizationcolorizationautomatic-colorization
      Python
      •
      Other
      •38•449•13•0•Updated Dec 10, 2025Dec 10, 2025

    • SEED-Voken

      Public
      SEED-Voken: A Series of Powerful Visual Tokenizers
      Python
      •
      Apache License 2.0
      •36•985•2•1•Updated Nov 25, 2025Nov 25, 2025

    • GenCompositor

      Public
      Official implementation of the paper "GenCompositor: Generative Video Compositing with Diffusion Transformer"
      video-editingdiffusion-modelsdiffusion-transformer
      Python
      •
      Other
      •5•131•3•0•Updated Nov 24, 2025Nov 24, 2025

    • ARC-Chapter

      Public
      Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries
      Apache License 2.0
      •0•27•1•0•Updated Nov 19, 2025Nov 19, 2025

    • BlobCtrl

      Public
      [SIGGRAPH ASIA'25] BlobCtrl: Taming Controllable Blob for Element-level Image Editing
      image-editingaigc
      Python
      •
      Other
      •2•24•1•0•Updated Nov 14, 2025Nov 14, 2025

    • RollingForcing

      Public
      Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
      real-timelong-contextlong-video-generationvideo-diffusion-modelefficient-tuning
      Python
      •
      Other
      •12•278•8•0•Updated Oct 31, 2025Oct 31, 2025

    • MindOmni

      Public
      Python
      •
      Other
      •1•139•2•0•Updated Oct 15, 2025Oct 15, 2025

    • vllm

      Public
      vllm for ARC-Hunyuan-Video-7B
      Python
      •
      Apache License 2.0
      •0•2•0•5•Updated Oct 6, 2025Oct 6, 2025

    • GeometryCrafter

      Public
      [ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
      depth-estimationvideo-to-4diccv2025
      Python
      •
      Other
      •17•416•3•0•Updated Oct 2, 2025Oct 2, 2025

    • Moto

      Public
      [ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
      Python
      •
      Other
      •5•152•6•0•Updated Oct 1, 2025Oct 1, 2025

    • ARC-Hunyuan-Video-7B

      Public
      Structured Video Comprehension of Real-World Shorts
      Python
      •
      Other
      •7•227•14•0•Updated Sep 21, 2025Sep 21, 2025

    • AudioStory

      Public
      AudioStory: Generating Long-Form Narrative Audio with Large Language Models
      video-to-audiodiffusion-modelstext-to-audioaudio-generationmultimodal-large-language-modelsvideo-dubbing
      Jupyter Notebook
      •18•291•3•1•Updated Sep 21, 2025Sep 21, 2025

    • IC-Custom

      Public
      [Arxiv'25] IC-Custom: Diverse Image Customization via In-Context Learning
      fluxapplicationimageimage-editingimage-inpaintingimage-customizationaigc
      Python
      •
      Other
      •3•157•1•0•Updated Sep 15, 2025Sep 15, 2025

    • BrushEdit

      Public
      [under review] The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"
      image-editingimage-inpaintingdiffusion-models
      Python
      •
      Other
      •28•586•11•0•Updated Sep 3, 2025Sep 3, 2025

    • ToonComposer

      Public
      Streamlining Cartoon Production with Generative Post-Keyframing
      Python
      •
      Other
      •45•518•8•0•Updated Aug 20, 2025Aug 20, 2025

    • TokLIP

      Public
      TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
      Python
      •
      Other
      •5•235•8•0•Updated Aug 18, 2025Aug 18, 2025

    • FreeSplatter

      Public
      [ICCV 2025] FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
      JavaScript
      •
      Other
      •14•211•10•2•Updated Aug 4, 2025Aug 4, 2025

    • TencentARC.github.io

      Public
      HTML
      •0•0•0•0•Updated Aug 1, 2025Aug 1, 2025

    • Video-Holmes

      Public
      Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
      Python
      •
      Apache License 2.0
      •2•82•2•0•Updated Jul 13, 2025Jul 13, 2025

    • SEED-Bench-R1

      Public
      Python
      •
      Apache License 2.0
      •2•95•2•0•Updated Jun 23, 2025Jun 23, 2025

    • GRPO-CARE

      Public
      Python
      •
      Apache License 2.0
      •2•79•5•0•Updated Jun 23, 2025Jun 23, 2025

    • AnimeGamer

      Public
      [ICCV 2025] AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
      Python
      •
      Other
      •28•341•5•1•Updated Apr 9, 2025Apr 9, 2025

    • VideoPainter

      Public
      [SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"
      videovideo-editingvideo-inpaintingvideo-dataset
      Python
      •
      Other
      •35•533•15•0•Updated Apr 8, 2025Apr 8, 2025

    • DiTCtrl

      Public
      [CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"
      Python
      •
      Other
      •9•318•8•0•Updated Mar 30, 2025Mar 30, 2025

    • DI-PCG

      Public
      Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".
      Python
      •
      Other
      •3•133•3•0•Updated Mar 23, 2025Mar 23, 2025

    • Divot

      Public
      Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)
      Python
      •
      Other
      •2•85•3•0•Updated Feb 27, 2025Feb 27, 2025

    • MotionCtrl

      Public
      Official Code for MotionCtrl [SIGGRAPH 2024]
      Python
      •
      Apache License 2.0
      •77•1.5k•29•0•Updated Feb 19, 2025Feb 19, 2025

    • ViT-Lens

      Public
      [CVPR 2024] ViT-Lens: Towards Omni-modal Representations
      multimodal-learning
      Python
      •
      Other
      •11•188•4•0•Updated Feb 3, 2025Feb 3, 2025

    • StereoCrafter

      Public
      A framework to convert any 2D videos to immersive stereoscopic 3D
      Python
      •
      Other
      •45•426•25•2•Updated Jan 7, 2025Jan 7, 2025