InternVL2_5-HiMTok-8B Open-source Model - Free for Precise and Efficient Image Segmentation Tasks

Internvl2 5 HiMTok 8B

Developed by yayafengzi

HiMTok is a hierarchical mask token learning framework fine-tuned on the InternVL2_5-8B large multimodal model, focusing on image segmentation tasks.

Image-to-Text

Safetensors

Open Source License:Apache-2.0 #Multimodal Image Segmentation #Hierarchical Mask Tokenization #Zero-shot Learning

Downloads 16

Release Time : 3/20/2025

Model Overview

This model achieves efficient image segmentation through a hierarchical mask token learning framework, particularly suitable for tasks on the refcoco series datasets.

Model Features

Hierarchical Mask Token Learning

Adopts a hierarchical structure for image segmentation tasks, improving segmentation accuracy and efficiency.

Multimodal Capability

Combines vision and language understanding to support complex image segmentation tasks.

Based on Large Pre-trained Models

Fine-tuned on InternVL2_5-8B, featuring powerful feature extraction capabilities.

Model Capabilities

Image Segmentation

Mask Generation

Multimodal Understanding

Vision-Language Task Processing

Use Cases

Computer Vision

Referring Image Segmentation

Segments specific regions in an image based on textual descriptions.

Performs well on the refcoco series datasets.

Interactive Image Editing

Guides image editing and modification through natural language instructions.

Property	Details
Base Model	OpenGVLab/InternVL2_5-8B
Pipeline Tag	mask-generation

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Internvl2 5 HiMTok 8B

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model

📚 Documentation

📄 License

📦 Model Details

📖 Citation

🔗 Links