Alternatives and similar repositories for Sa2VA

Users that are interested in Sa2VA are comparing it to the libraries listed below

• HarborYuan / ovsam
  [ECCV 2024] The official code of paper "Open-Vocabulary SAM".
  ☆1,002Updated last month
• lxtGH / OMG-Seg
  OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]
  ☆1,321Updated 3 months ago
• Mark12Ding / SAM2Long
  [ICCV 2025] SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
  ☆511Updated last month
• FoundationVision / Groma
  [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
  ☆578Updated last year
• DAMO-NLP-SG / VideoRefer
  [CVPR 2025] The code for "VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM"
  ☆265Updated last week
• NVlabs / EAGLE
  Eagle: Frontier Vision-Language Models with Data-Centric Strategies
  ☆865Updated last month
• FoundationVision / GLEE
  [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
  ☆1,151Updated 10 months ago
• ZiyuGuo99 / Image-Generation-CoT
  [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation
  ☆795Updated 3 months ago
• shenyunhang / APE
  [CVPR 2024] Aligning and Prompting Everything All at Once for Universal Visual Perception
  ☆588Updated last year
• ShareGPT4Omni / ShareGPT4Video
  [NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"
  ☆1,075Updated 11 months ago
• CircleRadon / Osprey
  [CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"
  ☆829Updated 3 weeks ago
• chongzhou96 / EdgeSAM
  Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
  ☆1,058Updated 3 months ago
• FoundationVision / Liquid
  Liquid: Language Models are Scalable and Unified Multi-modal Generators
  ☆613Updated 5 months ago
• Oryx-mllm / Oryx
  [ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
  ☆324Updated 2 months ago
• showlab / Show-o
  [ICLR 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
  ☆1,696Updated this week
• om-ai-lab / OmDet
  Real-time and accurate open-vocabulary end-to-end object detection
  ☆1,335Updated 8 months ago
• hustvl / EVF-SAM
  Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
  ☆465Updated 5 months ago
• Ola-Omni / Ola
  Ola: Pushing the Frontiers of Omni-Modal Language Model
  ☆365Updated 3 months ago
• MasterBin-IIAU / UNINEXT
  [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
  ☆1,278Updated 2 years ago
• NJU-PCALab / RAG-Diffusion
  [ICCV 2025] Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥
  ☆601Updated 2 months ago
• NVlabs / describe-anything
  [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
  ☆1,323Updated 2 months ago
• XueZeyue / DanceGRPO
  An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
  ☆774Updated this week
• SkyworkAI / Matrix-Game
  Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
  ☆1,606Updated 3 weeks ago
• microsoft / VidTok
  a family of versatile and state-of-the-art video tokenizers.
  ☆412Updated 2 weeks ago
• baaivision / See3D
  [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
  ☆685Updated 5 months ago
• alibaba / Tora
  [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation
  ☆1,198Updated 2 months ago
• yoxu515 / aot-benchmark
  An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
  ☆572Updated last year
• Vchitect / Vchitect-2.0
  Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
  ☆914Updated 5 months ago
• qqlu / Entity
  EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
  ☆1,032Updated last year
• AlaaLab / InstructCV
  [ ICLR 2024 ] Official Codebase for "InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists"
  ☆463Updated last year