Search Results for "visual-" - Page 9
Sort By:
Showing 530 open source projects for "visual-"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
VGGT
[CVPR 2025 Best Paper Award] VGGT
VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. The design emphasizes consistent geometric reasoning: outputs from one head (e.g., correspondences or tracks) reinforce others (e.g., pose or depth), making the system more robust to challenging viewpoints and textures. ... -
2
Perf Book
The book "Performance Analysis and Tuning on Modern CPU"
This project is a practical guide to performance analysis and tuning on modern CPUs, bridging microarchitecture details with hands-on profiling. It explains how caches, TLBs, prefetchers, branch predictors, and out-of-order execution influence real program speed, then connects those concepts to concrete optimization strategies. Readers learn how to design trustworthy benchmarks, avoid measurement traps (warmup, turbo, frequency scaling), and interpret hardware performance counters. The book... -
3
LLaMA-Mesh
Unifying 3D Mesh Generation with Language Models
...By serializing 3D geometry into text tokens, the approach allows existing transformer architectures to generate and interpret 3D models without requiring specialized visual tokenizers. The project includes a supervised fine-tuning dataset composed of interleaved text and mesh data, allowing the model to learn relationships between textual descriptions and 3D structures. As a result, the model can generate mesh models directly from text prompts, explain mesh structures in natural language, or output mixed text-and-mesh sequences. ... -
4
Paper2Slides
From Paper to Presentation in One Click
...It is designed to replace the repetitive work of turning dense technical documents into presentation-friendly structure by extracting key points, figures, and data into a coherent visual narrative. The system supports multiple input formats, so you can process PDFs and common office documents rather than being locked to a single file type. It uses an extraction approach intended to capture critical insights comprehensively, including important visuals and data points that often get missed in naive summarization. ... -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
AI-Codereview-Gitlab
GitLab automatic code review tool based on large models
AI-Codereview-Gitlab is an open-source automation tool that integrates large language models into the GitLab development workflow to perform automated code reviews. The system monitors GitLab repositories and analyzes commits or merge requests using AI models to identify potential issues, coding mistakes, and quality improvements before the code is merged. By leveraging multiple large language model providers—including OpenAI, DeepSeek, ZhipuAI, or local models through Ollama—the platform... -
6
InfiniteYou
Flexible Photo Recrafting While Preserving Your Identity
...Using an architecture built around diffusion transformers (DiTs), InfiniteYou introduces a component called InfuseNet that injects identity features derived from reference images into the generation process — via residual connections — so that the output matches the person’s identity closely, without sacrificing visual quality or text-image alignment. The team uses a multi-stage training strategy with synthetic multi-sample data per identity to fine-tune for both identity consistency and aesthetic quality. Compared to prior methods, InfiniteYou significantly improves on identity similarity, text-prompt adherence, overall image quality, and avoids common problems such as face copy-pasting artifacts. -
7
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel... -
8
OSWorld
Benchmarking Multimodal Agents for Open-Ended Tasks
...It provides a richly simulated 3D world where multiple agents can interact, perform tasks, and learn complex behaviors. OSWorld emphasizes multi-modal interaction, enabling agents to process visual, auditory, and symbolic data for grounded learning in a simulated world. -
9
CogVLM
A state-of-the-art open visual language model
CogVLM is an open-source visual–language model suite—and its GUI-oriented sibling CogAgent—aimed at image understanding, grounding, and multi-turn dialogue, with optional agent actions on real UI screenshots. The flagship CogVLM-17B combines ~10B visual parameters with ~7B language parameters and supports 490×490 inputs; CogAgent-18B extends this to 1120×1120 and adds plan/next-action outputs plus grounded operation coordinates for GUI tasks. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
DWSIM - Open Source Process Simulator
Simulate chemical processes using advanced thermodynamic models
DWSIM is an open source, CAPE-OPEN compliant chemical process simulator for Windows, Linux and macOS systems. Written in VB.NET and C#, DWSIM features a comprehensive set of unit operations, advanced thermodynamic models, support for reacting systems, petroleum characterization tools and a fully-featured graphical interface. DWSIM Pro is a commercial sibling of DWSIM built on top of open-source software. It offers extended features, comes with private support, and is accessible in the... -
11
InternVL
A Pioneering Open-Source Alternative to GPT-4o
InternVL is a large-scale multimodal foundation model designed to integrate computer vision and language understanding within a unified architecture. The project focuses on scaling vision models and aligning them with large language models so that they can perform tasks involving both visual and textual information. InternVL is trained on massive collections of image-text data, enabling it to learn representations that capture both visual patterns and semantic meaning. The model supports a wide variety of tasks, including visual perception, image classification, and cross-modal retrieval between images and text. It can also be connected to language models to enable conversational interfaces that understand images, videos, and other visual content. ... -
12
SCons
A software construction tool
SCons is a software construction tool that is a superior alternative to the classic "Make" build tool that we all know and love. SCons is implemented as a Python script and set of modules, and SCons "configuration files" are actually executed as Python scripts. This gives SCons many powerful capabilities not found in other software build tools. We make SCons available in three distinct packages, for different purposes. - The scons package is the basic package to install SCons. You... -
13
OpenPiano — Virtual Piano for Windows
Desktop piano playable with a PC keyboard, mouse, or MIDI device.
OpenPiano is a Windows desktop piano application that allows you to play, practice, and record music using your PC keyboard, mouse, or a MIDI device. It supports real-time playback using SoundFonts and provides on-screen piano layouts for visual feedback while playing. OpenPiano is designed to run entirely locally. It does not require accounts, cloud services, or an internet connection for core functionality. Project links: Website: https://www.justagwas.com/projects/openpiano GitHub: https://github.com/Justagwas/openpiano Documentation: https://github.com/Justagwas/openpiano/wiki The application is fully open source. ... -
14
HuMidi
Play MIDI like a human in ROBLOX with automatic sustain pedals.
...The pedals are generated with a thorough analysis of the MIDI data, adding more depth to your performance that no other MIDI players could! Personally have been tested in: - Visual Pianos - Starving Pianists - Digital Piano - Piano's Got Talent This tool is universal, as long as the piano in-game allows to be played on a keyboard. -
15
PySchool
Installable / Portable Python Distribution for Everyone.
PySchool is a free and open-source Python distribution intended primarily for students who learn Python and data analysis, but it can also used by scientists, engineering, and data scientists. It includes more than 150 Python packages (full edition) including numpy, pandas, scipy, sympy, keras, scikit-learn, matplotlib, seaborn, beautifulsoup4... -
16
LazyDS4
Transform your DualShock 4 into a native Xbox 360 controller. v2.1.0
...Optimized for simplicity and performance, it offers real-time input mapping with a ~1ms (1000Hz) polling rate, modern graphical interface with PyQt5, and automatic joystick calibration. 📌 What's New (v2.1.0) 🎨 Visual Overhaul — Modern, professional interface with gradient backgrounds and advanced styling 📐 Layout Optimization — Improved spacing, alignment, and responsiveness 🎉 Icon Integration — Consistent use of dynamic SVG icons throughout ⚡ Enhanced Button Design — Polished buttons with smooth animations and clear actions 📊 Responsive Interface — Adapted for various screen sizes without overlaps 🔔 Real-time Visual Indicators — Clear and immediate feedback for status, warnings, and battery levels Built by the lazy, for the lazy. -
17
OculiX
Visual Automation IDE — automate anything you see on screen
...Key features: - Guided step-by-step recorder with live code preview - Image recognition via OpenCV 4.10 - Dual OCR: Tesseract (built-in) + PaddleOCR (neural, high precision) - Local and remote automation via integrated VNC - SSH tunnels via embedded JSch - Cross-platform: Windows, macOS (Apple Silicon M1-M4), Linux - Scripting: Jython, JRuby, Java, PowerShell, AppleScript - Java 17 recommended (Java 8+ supported) - Full CI/CD with automated builds for all platforms Used worldwide for test automation, RPA, and visual regression testing. MIT License. Maintained by oculix-org. -
18
dashAI
dashAI: an interactive platform for training, evaluating and deploying
dashAI is an open-source, No-code workbench for Exploratory Data Analysis and classical ML. Visual data preparation, multi-model experiments, XAI explainability, and a plugin-based extensible catalog. The platform guides users through a complete, traceable workflow — data ingestion → visual exploration → preprocessing → model training → evaluation → explainability — without writing a single line of code. Each step is explicit and reversible, keeping the user in control rather than delegating decisions to an opaque pipeline. -
19
Equestria OS
An Arch Linux OS with 20+ custom GUI utilities & MLP theme customizer.
A user-friendly Linux distribution based on Arch Linux and KDE Plasma 6. Designed by a solo creator as a passion project, this lightweight operating system eliminates the need for terminal commands by offering over 20 unique, built-in graphical utilities for effortless computer management. Equestria OS makes your computer feel like home. It comes with a deeply integrated Proton Engine, allowing you to run your favorite Windows apps and games (.exe) with a simple double-click in secure,... -
20
Gammu
Cellular manager for mobile phones/modems
Gammu is a cellular manager for mobile phones/modems. It contains libraries and functions for ringtones,logos,phonebook,SMS,etc. (used by external software), a command line version (with backup/restore) and SMS gateway (with MySQL and PostgreSQL supp -
21
Universal runtime installer
This installer allows to install the latest Windows Runtimes
This installer allows to install the latest Visual C++ Runtime of all years (2008-2022), Full DirectX Runtime, Microsoft XNA Framework, .Net Runtime, Java and OpenAL at once. -
22
...THIS PROJECT HAS BEEN MOVED!! https://github.com/Lymphatus/caesium-image-compressor Caesium reduces the size of your picture up to 90%, preserving the original visual quality. Allows you to save a lot of space and easily upload your pictures on the web in a moment. The software is user-friendly with a simple and clear interface.
-
23
Wait and Pounce FT8
Wait to decode callsigns, then call them using UDP protocol
Neat alternative for JTAlert. Available for both Apple and Windows (10+). Make sure to automatically call any Wanted callsigns specified. Can also be used to monitor band opening. Can handle callsign exclusions. Can even handle wanted callsigns according to your worked before Rules. -
24
voxshare_gui
*VoxShare* is a simple Python-based push-to-talk multicast voice chat
VoxShare is a simple Python-based push-to-talk multicast voice chat application with a sleek modern GUI built using CustomTkinter. Provided as python source code or compiled standalone windows application (no need to install anything). -
25
Kirstens Viewers
Opensource Created Custom Viewers For Virtual Worlds like SecondLife.
...It’s built for creators, photographers, and advanced users who want a clean, modern viewer with a focus on high performance on high end PC's Anaglyph 3D Mode , OpenCL‑based Visual Effects, Aggressive Optimisation, vcpkg + PowerShell One‑Click Build Automation, Highly Tuned Graphics Path , Many Other Cutting‑Edge Features — ongoing experimental work, performance improvements, and creator‑driven enhancements continue to push the viewer forward.