Alternatives and similar repositories for VLM-Finetuning

Users that are interested in VLM-Finetuning are comparing it to the libraries listed below

• OpenGVLab / InternVL-MMDetSeg
  Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed
  ☆103Updated last year
• Xuan-World / Mamba-YOLO-World
  Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection
  ☆94Updated 7 months ago
• ShaohonChen / Qwen3-SmVL
  将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调
  ☆421Updated 2 months ago
• D-Robotics-AI-Lab / DOSOD
  A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space
  ☆90Updated 9 months ago
• AI-Study-Han / Zero-Qwen-VL
  训练一个对中文支持更好的LLaVA模型，并开源训练代码和数据。
  ☆75Updated last year
• PolyU-ChenLab / UniPixel
  🔮 UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning (NeurIPS 2025)
  ☆174Updated 2 weeks ago
• zhangfaen / finetune-InternVL2
  ☆30Updated last year
• WatchTower-Liu / VLM-learning
  Building a VLM model starts from the basic module.
  ☆18Updated last year
• IDEA-Research / Rex-Thinker
  Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning
  ☆127Updated 4 months ago
• xmu-xiaoma666 / Multimodal-Open-O1
  Multimodal Open-O1 (MO1) is designed to enhance the accuracy of inference models by utilizing a novel prompt-based approach. This tool wo…
  ☆29Updated last year
• xinyanghuang7 / Basic-Visual-Language-Model
  Build a simple basic multimodal large model from scratch. 从零搭建一个简单的基础多模态大模型🤖
  ☆47Updated last year
• hhaAndroid / awesome-mm-chat
  多模态 MM +Chat 合集
  ☆275Updated 2 months ago
• WeitaiKang / SegVG
  [ECCV 2024] SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
  ☆64Updated last year
• THU-MIG / YOLO-UniOW
  YOLO-UniOW: Efficient Universal Open-World Object Detection
  ☆163Updated 9 months ago
• Christinepan881 / DINO-R1
  ☆51Updated 4 months ago
• lorebianchi98 / CountingDINO
  Official implementation of the paper: “CountingDINO: A Training-free Pipeline for Exemplar-based Class-Agnostic Counting”
  ☆41Updated 5 months ago
• wanghao9610 / X-SAM
  X-SAM: From Segment Anything to Any Segmentation
  ☆304Updated last month
• dvlab-research / VisionReasoner
  Vision Manus: Your versatile Visual AI assistant
  ☆290Updated 3 weeks ago
• iMoonLab / Hyper-YOLOv1.1
  The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".
  ☆113Updated 10 months ago
• niki-amini-naieni / CountVid
  Includes the VideoCount dataset and CountVid code for the paper Open-World Object Counting in Videos.
  ☆79Updated 3 months ago
• bubbliiiing / DiT-pytorch
  这是一个DiT-pytorch的代码，主要用于学习DiT结构。
  ☆81Updated last year
• callsys / DynRefer
  [CVPR 2025] DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution
  ☆54Updated 8 months ago
• ding523 / Curr_REFT
  ☆72Updated 5 months ago
• ZhangXJ199 / TinyLLaVA-Video
  A Simple Framework of Small-scale LMMs for Video Understanding
  ☆96Updated 4 months ago
• BestAnHongjun / LMDeploy-Jetson
  Deploying LLMs offline on the NVIDIA Jetson platform marks the dawn of a new era in embodied intelligence, where devices can function ind…
  ☆102Updated last year
• OpenGVLab / PIIP
  [NeurIPS 2024 Spotlight ⭐️ & TPAMI 2025] Parameter-Inverted Image Pyramid Networks (PIIP)
  ☆105Updated 3 months ago
• FelixCaae / CrowdSAM
  [ECCV2024] Official implementation of Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
  ☆90Updated 6 months ago
• congvvc / HyperSeg
  [CVPR2025] Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".
  ☆171Updated 10 months ago
• yujunhuics / Reyes
  从零到一实现了一个多模态大模型，并命名为Reyes（睿视），R：睿，eyes：眼。Reyes的参数量为8B，视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct，Reyes也通过一个两层MLP投影层连…
  ☆26Updated 8 months ago
• lucasjinreal / Namo-R1
  A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
  ☆238Updated 6 months ago