Alternatives and similar repositories for realtime-video

Users that are interested in realtime-video are comparing it to the libraries listed below

• NVlabs / LongLive

  View on GitHub
  [ICLR 2026] LongLive: Real-time Interactive Long Video Generation
  ☆1,054Updated this week
• aigc-apps / VideoX-Fun

  View on GitHub
  📹 A more flexible framework that can generate videos at any resolution and creates videos from images.
  ☆1,891Feb 10, 2026Updated last week
• hao-ai-lab / FastVideo

  View on GitHub
  A unified inference and post-training framework for accelerated video generation.
  ☆3,086Updated this week
• tianweiy / CausVid

  View on GitHub
  (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  ☆1,215Aug 7, 2025Updated 6 months ago
• KlingTeam / UniVideo

  View on GitHub
  [ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos
  ☆425Updated this week
• justincui03 / Self-Forcing-Plus-Plus

  View on GitHub
  Official Repo for Self-Forcing++ High Quality Long Video Generation
  ☆235Oct 13, 2025Updated 4 months ago
• zai-org / SCAIL-Pose

  View on GitHub
  Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representat…
  ☆177Dec 28, 2025Updated last month
• huggingface / finetrainers

  View on GitHub
  Scalable and memory-optimized training of diffusion models
  ☆1,335Jun 4, 2025Updated 8 months ago
• bytedance / ATI

  View on GitHub
  Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944
  ☆336Aug 7, 2025Updated 6 months ago
• IGL-HKUST / DiffusionAsShader

  View on GitHub
  [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
  ☆804Jun 9, 2025Updated 8 months ago
• chenfengxu714 / StreamDiffusionV2

  View on GitHub
  StreamDiffusion, Live Stream APP
  ☆351Feb 7, 2026Updated last week
• TQTQliu / Light-X

  View on GitHub
  [ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control
  ☆166Dec 11, 2025Updated 2 months ago
• TencentARC / RollingForcing

  View on GitHub
  [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
  ☆322Oct 31, 2025Updated 3 months ago
• kxhit / cvpr25_oral_gpu_info

  View on GitHub
  Just wanna see what type and how many GPUs/TPUs are used in CVPR 2025 oral papers. Fun vibe coding with LLMs.
  ☆12Apr 24, 2025Updated 9 months ago
• JaredTherriault / Rope

  View on GitHub
  GUI-focused roop
  ☆15Mar 6, 2025Updated 11 months ago
• Yaofang-Liu / Pusa-VidGen

  View on GitHub
  Pusa: Thousands Timesteps Video Diffusion Model
  ☆671Updated this week
• silent-chen / AutoPartGen

  View on GitHub
  ☆120Jul 19, 2025Updated 6 months ago
• stdstu12 / YUME

  View on GitHub
  The official code of Yume
  ☆612Jan 14, 2026Updated last month
• FoundationVision / InfinityStar

  View on GitHub
  [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
  ☆715Nov 27, 2025Updated 2 months ago
• ali-vilab / Wan-Move

  View on GitHub
  [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
  ☆563Jan 5, 2026Updated last month
• BigAandSmallq / SAD

  View on GitHub
  Official implementation of "Towards One-Step Causal Video Generation via Adversarial Self-Distillation" (arXiv 2025). A novel framework f…
  ☆25Nov 4, 2025Updated 3 months ago
• TencentARC / DiTCtrl

  View on GitHub
  [CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Long…
  ☆320Mar 30, 2025Updated 10 months ago
• KlingAIResearch / ReCamMaster

  View on GitHub
  [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
  ☆1,739Nov 28, 2025Updated 2 months ago
• ModelTC / LightX2V

  View on GitHub
  Light Image Video Generation Inference Framework
  ☆1,939Feb 10, 2026Updated last week
• guandeh17 / Self-Forcing

  View on GitHub
  Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
  ☆3,135Sep 12, 2025Updated 5 months ago
• EzioBy / Ditto

  View on GitHub
  [Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
  ☆567Oct 29, 2025Updated 3 months ago
• pPetrichor / WorldCanvas

  View on GitHub
  ☆130Dec 19, 2025Updated last month
• KlingAIResearch / VideoAlign

  View on GitHub
  [NeurIPS 2025] Improving Video Generation with Human Feedback
  ☆424Sep 24, 2025Updated 4 months ago
• X-Omni-Team / X-Omni

  View on GitHub
  Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).
  ☆420Aug 26, 2025Updated 5 months ago
• Passenger12138 / attention-map-diffusers-vdm

  View on GitHub
  ☆12Feb 13, 2025Updated last year
• yangzhou24 / OmniWorld

  View on GitHub
  [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
  ☆429Jan 7, 2026Updated last month
• jy0205 / Pyramid-Flow

  View on GitHub
  [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
  ☆3,159Dec 21, 2024Updated last year
• ByteDance-Seed / Bagel

  View on GitHub
  Open-source unified multimodal model
  ☆5,654Oct 27, 2025Updated 3 months ago
• zai-org / RealVideo

  View on GitHub
  A real-time streaming conversational video system that transforms text interactions into continuous, high-fidelity video responses using …
  ☆297Dec 15, 2025Updated 2 months ago
• alibaba / identity-grpo

  View on GitHub
  Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
  ☆180Oct 21, 2025Updated 3 months ago
• snap-research / MSRVTT-Personalization

  View on GitHub
  Benchmark dataset and code of MSRVTT-Personalization
  ☆52Nov 10, 2025Updated 3 months ago
• Tencent-Hunyuan / HunyuanCustom

  View on GitHub
  HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
  ☆1,205Oct 15, 2025Updated 4 months ago
• WindVChen / V2M4

  View on GitHub
  A novel 4D reconstruction method that directly generates high-quality, animation-ready 4D mesh asset (.GLB file) from a single monocular …
  ☆117Nov 24, 2025Updated 2 months ago
• ByteDance-Seed / TraceAnything

  View on GitHub
  [ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields
  ☆501Oct 31, 2025Updated 3 months ago