Alternatives and similar repositories for VAR

Users that are interested in VAR are comparing it to the libraries listed below

• facebookresearch / DiT
  Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
  ☆7,793Updated last year
• mini-sora / minisora
  MiniSora: A community aims to explore the implementation path and future development direction of Sora.
  ☆1,265Updated 6 months ago
• EvolvingLMMs-Lab / lmms-eval
  One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
  ☆3,060Updated this week
• jingyi0000 / VLM_survey
  Collection of AWESOME vision-language models for vision tasks
  ☆2,914Updated 3 months ago
• PKU-YuanGroup / Open-Sora-Plan
  This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
  ☆12,020Updated last month
• NUS-HPC-AI-Lab / VideoSys
  VideoSys: An easy and efficient system for video generation
  ☆2,000Updated 2 weeks ago
• dvlab-research / MGM
  Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
  ☆3,314Updated last year
• PKU-YuanGroup / MagicTime
  [TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
  ☆1,335Updated last month
• LLaVA-VL / LLaVA-NeXT
  ☆4,202Updated last week
• Vchitect / Latte
  [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
  ☆1,870Updated 5 months ago
• ytongbai / LVM
  ☆1,831Updated last year
• showlab / Show-o
  [ICLR 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
  ☆1,696Updated this week
• FoundationVision / LlamaGen
  Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
  ☆1,858Updated last year
• PKU-Alignment / align-anything
  Align Anything: Training All-modality Model with Feedback
  ☆4,544Updated 3 weeks ago
• ChenHsing / Awesome-Video-Diffusion-Models
  [CSUR] A Survey on Video Diffusion Models
  ☆2,193Updated 2 months ago
• dvlab-research / LISA
  Project Page for "LISA: Reasoning Segmentation via Large Language Model"
  ☆2,395Updated 7 months ago
• PixArt-alpha / PixArt-alpha
  PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
  ☆3,185Updated 10 months ago
• baaivision / Emu3
  Next-Token Prediction is All You Need
  ☆2,195Updated 5 months ago
• LTH14 / mar
  PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
  ☆1,732Updated 11 months ago
• NUS-HPC-AI-Lab / Neural-Network-Diffusion
  We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard laten…
  ☆878Updated 8 months ago
• TencentARC / BrushNet
  [ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"
  ☆1,656Updated 8 months ago
• Tencent-Hunyuan / HunyuanDiT
  Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
  ☆4,237Updated 8 months ago
• fudan-generative-vision / champ
  [ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
  ☆4,232Updated last year
• FoundationVision / Infinity
  [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
  ☆1,431Updated 2 months ago
• Alpha-VLLM / Lumina-T2X
  Lumina-T2X is a unified framework for Text to Any Modality Generation
  ☆2,220Updated 7 months ago
• showlab / Awesome-Video-Diffusion
  A curated list of recent diffusion models for video generation, editing, and various other applications.
  ☆5,004Updated 3 weeks ago
• LTH14 / fractalgen
  PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437
  ☆1,159Updated 6 months ago
• cambrian-mllm / cambrian
  Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
  ☆1,949Updated 10 months ago
• facebookresearch / vggt
  [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
  ☆10,829Updated 2 weeks ago
• NVlabs / VILA
  VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…
  ☆3,528Updated last month