Search Results for "visual" - Page 3
Sort By:
Showing 474 open source projects for "visual"
View related business solutions-
Native Teams: Payments and Employment for International TeamsWith Native Teams’ Employer of Record (EOR) service, you can compliantly hire in 85+ countries without setting up a legal entity. From dedicated employee support and localised benefits to tax optimisation, we help you build a global team that feels truly cared for.
-
EasySend is a no-code platform that transforms customer journeysEvolve forms into smart, AI-powered digital workflows that streamline your data intake and elevate customer experiences.
-
1
HunyuanVideo-Foley
Multimodal Diffusion with Representation Alignment
HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan for high-fidelity Foley (sound effects) audio generation synchronized to video scenes. It is designed to generate audio that matches both visual content and textual semantic cues, for use in video production, film, advertising, games, etc. The model architecture aligns audio, video, and text representations to produce realistic synchronized soundtracks. Produces high-quality 48 kHz audio output suitable for professional use. Hybrid architecture combining multimodal transformer blocks and unimodal refinement blocks. ... -
2
LLM Vision
Visual intelligence for your home.
...The project enables Home Assistant to analyze images, video files, and live camera feeds using vision-capable AI models. Instead of relying only on traditional object detection pipelines, it allows users to send prompts about visual content and receive contextual descriptions or answers about what is happening in camera footage. The system can process events from surveillance platforms such as Frigate and convert them into meaningful summaries, notifications, or structured data for automation workflows. It also maintains a timeline of analyzed camera events that can be displayed in dashboards or queried through the assistant interface. -
3
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
...or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). While the internal architecture details are not fully documented publicly, the repo suggests that VL2 introduces enhancements over prior vision-language models (e.g. better scaling, cross-modal attention, more robust alignment) to improve grounding and multimodal understanding. -
4
LatentSync
Taming Stable Diffusion for Lip Sync
...The system leverages a U-Net diffusion backbone, with cross-attention of audio embeddings (via an audio encoder) and reference video frames to guide generation, and applies a set of loss functions (temporal, perceptual, sync-net based) to enforce lip-sync accuracy, visual fidelity, and temporal consistency. Over versions, LatentSync has improved temporal stability and lowered resource requirements — making inference more practical (e.g. 8 GB VRAM for earlier versions, somewhat higher for latest models). -
SalesTarget.ai | AI-Powered Lead Generation, Email Outreach, and CRMSalesTarget is ideal for B2B sales teams, startup founders, and marketing professionals looking to streamline lead generation and outreach. It also benefits growing SaaS companies and agencies aiming to scale their outbound efforts efficiently.
-
5
PaperBanana
Extension of Google Research’s PaperBanana
PaperBanana is an open-source agentic framework designed to automatically generate publication-quality academic diagrams and statistical plots directly from text descriptions. The project focuses on helping researchers, educators, and data scientists transform conceptual descriptions of figures into structured visual outputs suitable for research papers, presentations, and technical reports. Instead of manually designing charts or diagrams using traditional visualization tools, users can describe the desired figure in natural language and allow the system to generate the visual representation automatically. PaperBanana integrates modern multimodal AI models capable of interpreting instructions and producing graphics that follow academic conventions. ... -
6
Super Magic
All-in-one AI productivity platform with agents, workflows, and IM
...Magic centers around a general-purpose AI agent system called Super Magic, which can autonomously understand tasks, plan actions, execute workflows, and perform error correction. Alongside this, Magic includes a visual workflow engine that enables users to design complex AI processes using a drag-and-drop interface without requiring extensive coding knowledge. It also provides an enterprise-grade instant messaging system that integrates AI conversations with internal communication, allowing teams to collaborate while leveraging intelligent assistants. ... -
7
A.I.G
Full-stack AI Red Teaming platform
...Users can deploy it via Docker or scripts to get a modern web UI that guides them through tasks like scanning third-party frameworks for known CVEs and experimenting with prompt security against attack vectors. The tool provides both a visual interface and a comprehensive API, making integration with internal security systems or CI/CD pipelines practical for ongoing risk management. -
8
GLM-4.5V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.5V is the preceding iteration in the GLM-V series that laid much of the groundwork for general multimodal reasoning and vision-language understanding. It embodies the design philosophy of mixing visual and textual modalities into a unified model capable of general-purpose reasoning, content understanding, and generation, while already supporting a wide variety of tasks: from image captioning and visual question answering to content recognition, GUI-based agents, video understanding, and long-document interpretation. GLM-4.5V emerged from a training framework that leverages scalable reinforcement learning (with curriculum sampling) to boost performance across tasks ranging from STEM problem solving to long-context reasoning, giving it broad applicability beyond narrow benchmarks. ... -
9
Watermark Anything
Official implementation of Watermark Anything with Localized Messages
...Developed by Facebook Research, it provides a robust, flexible system that allows users to insert one or multiple watermarks within selected image regions while maintaining visual quality and recoverability. Unlike traditional watermarking methods that rely on uniform embedding, WAM supports spatially localized watermarks, enabling targeted protection of specific image regions or objects. The model is trained to balance imperceptibility, ensuring minimal visual distortion, with robustness against transformations and edits such as cropping or motion. -
Accounting practice management softwareCanopy is a cloud-based practice management software for accounting and tax firms, offering tools for client engagement, document management, workflow automation, and time & billing. Its Client Engagement platform centralizes interactions with a secure portal, customizable branding, and email integration, while the Document Management system enables organized, paperless file storage. The Workflow module enhances visibility into tasks and projects through templates, task assignments, and automation, reducing human error. Additionally, the Time & Billing feature tracks billable hours, generates invoices, and processes payments, ensuring accurate financial management. With its comprehensive features, Canopy streamlines operations, reduces stress, and enhances client experiences.
-
10
DriveLM
Driving with Graph Visual Question Answering
DriveLM is a research-oriented framework and dataset designed to explore how vision-language models can be integrated into autonomous driving systems. The project introduces a new paradigm called graph visual question answering that structures reasoning about driving scenes through interconnected tasks such as perception, prediction, planning, and motion control. Instead of treating autonomous driving as a purely sensor-driven pipeline, DriveLM frames it as a reasoning problem where models answer structured questions about the environment to guide decision making. ... -
11
LlamaGen
Autoregressive Model Beats Diffusion
LlamaGen is an open-source research project that introduces a new approach to image generation by applying the autoregressive next-token prediction paradigm used in large language models to visual generation tasks. Instead of relying on diffusion models, the framework treats images as sequences of tokens that can be generated progressively using transformer architectures similar to those used for text generation. The project explores how scaling autoregressive models and improving image tokenization techniques can produce competitive results compared with modern diffusion-based image generators. ... -
12
LISA
LISA: Reasoning Segmentation via Large Language Model
...The project introduces a framework where a large language model can interpret natural language instructions and produce segmentation masks that highlight relevant regions in an image. Instead of relying solely on predefined object categories, the model is capable of reasoning about complex textual queries and translating them into visual segmentation outputs. This approach allows the system to identify objects or regions in images based on semantic descriptions, contextual reasoning, and world knowledge. The model integrates multimodal capabilities by combining language understanding with visual perception so that text instructions guide the segmentation process. ... -
13
StarVector
StarVector is a foundation model for SVG generation
...The system treats vector graphics creation as a code generation problem, producing SVG code that can render detailed vector images. Its architecture combines computer vision techniques with language modeling capabilities so it can understand visual inputs and textual prompts simultaneously. The model converts raster images or text instructions into structured vector representations, enabling high-quality vectorization and design generation. This approach allows StarVector to create scalable graphics that maintain visual quality regardless of resolution, which is especially useful for design tools and illustration workflows. ... -
14
FastVLM
This repository contains the official implementation of FastVLM
...The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
15
ML Ferret
Refer and Ground Anything Anywhere at Any Granularity
Ferret is Apple’s end-to-end multimodal large language model designed specifically for flexible referring and grounding: it can understand references of any granularity (boxes, points, free-form regions) and then ground open-vocabulary descriptions back onto the image. The core idea is a hybrid region representation that mixes discrete coordinates with continuous visual features, so the model can fluidly handle “any-form” referring while maintaining precise spatial localization. The repo presents the vision-language pipeline, model assets, and paper resources that show how Ferret answers questions, follows instructions, and returns grounded outputs rather than just text. In practice, this enables tasks like “find that small red icon next to the chart and describe it” where both the linguistic reference and the visual region are ambiguous without fine spatial reasoning. -
16
MoCo (Momentum Contrast)
Self-supervised visual learning using momentum contrast in PyTorch
MoCo is an open source PyTorch implementation developed by Facebook AI Research (FAIR) for the papers “Momentum Contrast for Unsupervised Visual Representation Learning” (He et al., 2019) and “Improved Baselines with Momentum Contrastive Learning” (Chen et al., 2020). It introduces Momentum Contrast (MoCo), a scalable approach to self-supervised learning that enables visual representation learning without labeled data. The core idea of MoCo is to maintain a dynamic dictionary with a momentum-updated encoder, allowing efficient contrastive learning across large batches. ... -
17
Microsoft Azure CLI
Azure command-line interface
...We support tab completion for groups, commands, and some parameters. You can use the --query parameter and the JMESPath query syntax to customize your output. With the Azure CLI Tools Visual Studio Code extension, you can create .azcli files and use these features. IntelliSense for commands and their arguments. Snippets for commands, inserting required arguments automatically. Run the current command in the integrated terminal. Run the current command and show its output in a side-by-side editor. Show documentation on mouse hover. ... -
18
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
CogView4 is the latest generation in the CogView series of vision-language foundation models, developed as a bilingual (Chinese and English) open-source system for high-quality image understanding and generation. Built on top of the GLM framework, it supports multimodal tasks including text-to-image synthesis, image captioning, and visual reasoning. Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. It emphasizes bilingual usability, making it well-suited for cross-lingual multimodal applications. ... -
19
DINOv3
Reference PyTorch implementation and models for DINOv3
DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. ... -
20
Book5_Essentials-Probability-Statistics
The book 5 of statistics in simplicity
Book5_Essentials-of-Probability-and-Statistics is a Visualize-ML educational volume that introduces the statistical and probabilistic concepts underpinning modern data analysis and machine learning. The repository explains topics such as distributions, sampling, inference, and uncertainty using visual demonstrations and intuitive narratives. Its teaching philosophy prioritizes conceptual clarity over heavy formalism, making statistical thinking more approachable for beginners. The material connects probability theory directly to real analytical workflows, helping learners understand how statistics supports predictive modeling. ... -
21
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything
...It supports labeling tasks across images and videos and enables developers to prepare training datasets for tasks such as object detection, segmentation, classification, tracking, and pose estimation. The tool is built with an interactive graphical interface that simplifies annotation workflows and allows users to draw and edit labels directly on visual data. It also supports a wide range of export formats compatible with popular machine learning pipelines, making it easier to integrate with training frameworks. -
22
Conan
The open-source C/C++ package manager
The open-source, decentralized and multi-platform package manager to create and share all your native binaries. All platforms. Windows, Linux, Apple, FreeBSD, Android, iOS, embedded, cross-building, bare metal, etc. All build systems. Visual Studio MSBuild, CMake, Makefiles, SCons, etc. Extensible to any build system. Full management of binaries. Create, manage and reuse any number of binaries, for any configuration: platform, compiler, version, architectures, or build from sources at will. Fully automated dependency management. Transitive dependencies, conflicts detection, dependency overriding, conditional dependencies. ... -
23
machine-learning-refined
Master the fundamentals of machine learning, deep learning
machine-learning-refined is an educational repository designed to help students and practitioners understand machine learning algorithms through intuitive explanations and interactive examples. The project accompanies a series of textbooks and teaching materials that focus on making machine learning concepts accessible through visual demonstrations and simple code implementations. Instead of presenting algorithms purely through mathematical derivations, the repository emphasizes geometric intuition, visualization, and step-by-step experimentation. It includes Jupyter notebooks and scripts that illustrate core machine learning topics such as regression, classification, optimization methods, and neural networks. ... -
24
VMZ (Video Model Zoo)
VMZ: Model Zoo for Video Modeling
The codebase was designed to help researchers and practitioners quickly reproduce FAIR’s results and leverage robust pre-trained backbones for downstream tasks. It also integrates Gradient Blending, an audio-visual modeling method that fuses modalities effectively (available in the Caffe2 implementation). Although VMZ is now archived and no longer actively maintained, it remains a valuable reference for understanding early large-scale video model training, transfer learning, and multimodal integration strategies that influenced modern architectures like SlowFast and X3D. -
25
Agent S
Agent S: an open agentic framework that uses computers like a human
...The latest version, Agent S3, surpasses human-level performance on the OSWorld benchmark, demonstrating state-of-the-art results in complex multi-step computer tasks. Agent S combines powerful foundation models (such as GPT-5) with grounding models like UI-TARS to translate visual inputs into precise executable actions. It supports flexible deployment via CLI, SDK, or cloud, and integrates with multiple model providers including OpenAI, Anthropic, Gemini, Azure, and Hugging Face endpoints. With optional local code execution, reflection mechanisms, and compositional planning, Agent S provides a scalable and research-driven framework for building advanced computer-use agents.
