Projects sharing features with Grounded Segment Anything

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

GLM-4 is a large language model and fine-tuning framework designed for human-like text production, complex reasoning, and multilingual conversation. It functions as a multimodal system capable of processing high-resolution visual content and as a long-context model designed to analyze documents with a context window of up to one million tokens. The project differentiates itself through a function calling interface that enables AI agent development by connecting the model to external APIs and real-time web browsing. It includes specialized capabilities for generating functional programming cod

Narrator is an artificial intelligence system that converts real-time video feeds into natural language audio descriptions. It functions as a multimodal vision narrator and scene descriptor, using computer vision to transform environmental data from a camera into synthetic speech. The tool operates as a pipeline that captures periodic images from a feed and uses a multimodal large language model to analyze visual events. These analyses are then converted via text-to-speech synthesis into a voiceover that describes real-world activities and surroundings. The system supports automated environm

FastSAM is an image segmentation framework that uses convolutional neural networks to isolate visual elements and generate masks for detectable objects within images. It provides a system for both automatic all-object segmentation and promptable image segmentation. The project utilizes an inference-optimized architecture to reduce computational overhead, enabling faster mask generation and real-time visual analysis. It supports the creation of precise masks through various prompt inputs, including points, bounding boxes, and text descriptions. The framework covers broader computer vision cap

Bard-API is an asynchronous Python wrapper and client for interacting with Google Gemini. It functions as a stateful conversation manager and multimodal interface, allowing users to send text and image prompts to a language model and retrieve responses. The library utilizes a cookie-based authentication system that extracts session tokens from local browser storage to authorize requests. To manage access and connectivity, it includes proxy-based request routing to bypass regional restrictions and avoid IP blocks. The project covers capabilities for multimodal AI analysis and the maintenance

Blinko is a personal knowledge management system and an LLM-powered knowledge base that enables users to capture and organize thoughts through a bi-directional knowledge graph. It functions as a RAG-enabled note-taking application and a self-hosted Markdown editor, allowing for the creation of permanent documentation and fleeting notes. The project distinguishes itself by integrating retrieval-augmented generation to provide conversational querying and AI-powered analysis of private document libraries. It supports both cloud-based and local AI model integration, enabling users to perform sema

Serve is a multimodal AI orchestrator and inference server designed for deploying and scaling machine learning models as cloud-native services. It functions as a containerized workflow engine and distributed service mesh that routes multimodal data through connected execution units. The framework provides specialized capabilities for large language models, including a token streaming gateway that delivers generated text incrementally to reduce perceived latency. It distinguishes itself by enabling the chaining of executors into complex data processing pipelines and the orchestration of these

Screenshot-to-code is an AI visual frontend generator that translates images, design mockups, and screenshots into structured HTML, CSS, and Tailwind markup. It functions as a design-to-code converter that uses large language models and neural networks to transform visual elements into functional web page layouts. The tool automates the frontend design process by converting static mockups into website code, facilitating rapid UI prototyping and the generation of static website structures. It bridges the gap between visual design assets and frontend development by translating image-based layou

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

The nexa-sdk is an on-device AI SDK and multimodal inference engine designed to run large language, vision, and audio models locally on mobile and desktop hardware. It functions as a local LLM runtime and NPU acceleration framework, enabling the execution of generative and discriminative models without reliance on cloud services. The project distinguishes itself through a dedicated NPU acceleration framework that optimizes model execution on Neural Processing Units to reduce latency and power consumption. It employs hardware-agnostic backend routing to dynamically distribute computations acro

OmniParser is a multimodal interaction engine designed to function as a desktop automation agent. It interprets visual screen information to execute complex, multi-step tasks across operating system environments by bridging visual interface perception with language models. Through a continuous cycle of observation and command execution, the system grounds high-level natural language instructions into precise, coordinate-based actions. The project distinguishes itself by utilizing vision-based parsing to interact with software interfaces without requiring access to underlying application progr

This repository serves as an educational resource and technical guide for developers learning to integrate large language models into software applications. It provides practical lessons and code examples focused on building systems that perform automated text generation, data analysis, and interactive chat tasks. The project functions as a framework for understanding how to connect applications to external artificial intelligence services. It covers the implementation of secure authentication, the orchestration of network requests, and the configuration of model parameters such as temperatur

DeepSeek-VL2 is a multimodal large language model and vision-language system designed to analyze visual scenes and generate descriptive text. It functions as a visual question answering and visual grounding model, capable of extracting information from documents and locating specific objects or regions within images based on textual descriptions. The project utilizes a mixture-of-experts architecture to process combined image and text inputs. It is optimized for inference through incremental prefilling, which reduces the GPU memory requirements on hardware. The model covers multimodal data a

Streamer-Sales is a digital avatar video generator and large language model sales agent framework. It functions as a multimodal AI pipeline that synthesizes talking-head videos using text-to-speech and face animation to create virtual spokespeople. The system differentiates itself by combining retrieval-augmented generation with agentic web searching to ground product descriptions and sales scripts in factual data and real-time information. It further integrates a multimodal interaction workflow that coordinates automatic speech recognition and text-to-speech for real-time voice conversations

CogVLM is a multimodal large language model designed for visual reasoning and multi-turn dialogue. It functions as a visual grounding model and a quantized vision model, combining text and image processing to perform complex understanding and maintain context across visual inputs. The project includes capabilities as a GUI automation agent, allowing it to analyze application screenshots, plan operational steps, and return precise screen coordinates for interface interaction. It further supports visual grounding by generating bounding box coordinates to map text descriptions to specific spatia

BEVFormer is a perception framework that transforms multi-camera images into bird's-eye-view representations for autonomous driving. It functions as a multi-camera vision pipeline that integrates multiple camera streams into a single unified spatial perspective to facilitate environmental understanding. The system implements a transformer-based architecture that employs query-based feature extraction and spatiotemporal networks to aggregate spatial image features and temporal historical data. It uses recurrent temporal accumulation to maintain a persistent memory of the scene across consecuti

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

ml-ferret is a multimodal large language model framework and visual reasoning engine designed to reason about images and user interfaces. It functions as a UI grounding model and referring expression comprehension tool that maps natural language descriptions to precise pixel coordinates. The system focuses on high-resolution image analysis to identify and locate specific interface components. It employs multi-resolution image processing and region-aware visual encoding to preserve detail across different aspect ratios, enabling the model to analyze spatial relationships and functional layouts

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Bilive is a multimodal AI video pipeline and live stream recording tool designed to capture real-time broadcasts and automate the creation of highlight clips. It functions as a multi-platform stream orchestrator capable of distributing looped pre-recorded content and managing the automated upload of processed video clips to various destinations. The system distinguishes itself through AI-driven content generation, using comment density to detect high-energy segments and multimodal models to automatically produce descriptive titles and synchronized subtitles. It further utilizes image-to-image

Jina is a cloud-native framework for building and deploying multimodal AI applications that process text, images, and audio across distributed microservices. It functions as an inference orchestrator and a distributed model gateway, providing a containerized stack to organize AI executors into operational pipelines. The system manages large language model workloads through token-streamed response delivery and dynamic batching to increase hardware throughput. It utilizes a protocol-agnostic communication layer to route data across different machine learning frameworks. The framework covers hi

This project is a multi-modal image segmentation framework and a text-to-mask vision model. It serves as a SAM-based visual segmenter designed to isolate distinct objects within images and video by converting natural language prompts and other inputs into pixel-level semantic masks. The system functions as a multi-modal image segmentation framework that integrates text, image, and audio signals to generate masks. It includes an interactive video object tracker that isolates and tracks visual entities across video frames using referring images or textual queries. The framework provides capabi

pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D image. It utilizes pixel-aligned implicit functions to map image pixels to 3D space, predicting surface occupancy and distance to create detailed geometry. The system includes a pipeline for creating digital human assets, moving from 2D image feature projection to the extraction of discrete triangular meshes. It features specialized tools for refining these models, including a post-processor that removes geometric artifacts by isolating the largest connected component of the mesh.

sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human mesh recovery model to reconstruct full-body meshes, including the body, hands, and feet, from a single image. The project implements a specialized extension of the Segment Anything Model to guide the extraction and refinement of human body shapes. This integration allows for prompt-guided mesh recovery, where 2D masks and keypoints constrain the inference of 3D pose and shape parameters. The system covers a range of computer vision capabilities, including 3D spatial alignment t

Inpaint-Anything is a diffusion-based image editor and inpainting tool designed to remove or replace objects in images, videos, and 3D scenes. It functions as a text-guided manipulator that uses natural language descriptions and mask-based filling to modify visual content. The system provides specialized capabilities for multi-view 3D scene editing and video object removal. It tracks selected objects across multiple frames or perspectives to synthesize consistent backgrounds and maintain spatial coherence after an element is removed. The tool covers a range of image manipulation tasks, inclu