Search Results for "mask"
Sort By:
Showing 221 open source projects for "mask"
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.
-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
1
Mask Network
The portal to the new, open Internet
Mask Network brings privacy and benefits from Web3 to social media like Facebook & Twitter - with an open-sourced browser extension. Use the Mask Extension to hide your content from prying eyes and allow only your target audience to see it. If you’re launching a new project on the Ethereum, BSC, Polygon, or Arbitrum networks, ITOs are a completely new way of launching decentralized assets fairly. -
2
Segment Anything
Provides code for running inference with the SegmentAnything Model
...Because SAM was trained with an extremely large and diverse mask dataset, it tends to generalize well to new domains, making it a practical starting point for research and production annotation tools. -
3
Mask of Death is an app to let you spoof your MAC address. I reworked this from v. 1.0. Now at 1.5 it has worked great with all adapters I tried it with. *Note: it must be run with Admin privileges.
-
4
Neosync
Open Source Data Security Platform for Developers to Monitor
Neosync is a secure, open-source platform to generate, mask, and sync realistic test data across environments. It helps engineering teams create privacy-compliant datasets using synthetic data, transformations, and pseudonymization techniques. Designed with extensibility and data governance in mind, Neosync integrates with common databases and cloud services, enabling safe test environments for development and QA. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
ComfyUI Essentials
Essential nodes that are weirdly missing from ComfyUI core
...The extension is useful for creators who build complex ComfyUI graphs and need more control over image and mask manipulation. It is currently in maintenance-only mode, so it is best treated as a stable utility pack rather than an actively expanded feature set. -
6
WanGP
AI video generator optimized for low VRAM and older GPUs use
...Wan2GP provides a full web-based interface that simplifies interaction with complex generative pipelines, making it easier to configure prompts, models, and rendering settings. It also integrates a wide range of utilities such as prompt enhancement, mask editing, motion design, and extraction tools for pose, depth, and flow data to support advanced video workflows. -
7
folderify
Generate pixel-perfect macOS folder icons in the native style
...You can only assign one version of an icon to a folder. Dark color scheme is only supported for macOS 11.0 (and later) right now. Make sure the corner pixels of the mask image are transparent. They are used for empty margins. -
8
Mesh R-CNN
code for Mesh R-CNN, ICCV 2019
...The system combines 2D detection from Mask R-CNN with 3D reasoning modules that output full mesh reconstructions aligned with the input image. It has been evaluated on datasets such as Pix3D, where it demonstrates state-of-the-art performance in reconstructing real-world object geometry. -
9
GPT Image Playground
OpenAI gpt-image-2 API
GPT Image Playground is a web-based image generation and editing interface built around OpenAI’s GPT Image APIs and compatible providers. It gives users a clean UI for text-to-image generation, reference-image workflows, and mask-based editing. The project supports OpenAI-compatible endpoints, fal.ai, and custom HTTP providers, which makes it flexible for different image backend setups. It stores history and generated assets locally in the browser, keeping the user’s creative records out of third-party storage by default. The interface includes parameter tracking, batch workflows, configuration management, and comparison between requested and actually applied generation settings. ... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
PasteGuard
Masks sensitive data and secrets before they reach AI
...It sits between an application and the LLM provider, automatically replacing names, emails, tokens, and other personally identifiable information (PII) with placeholders so that external services never see raw sensitive values, and then optionally unmasking them in the returned output. PasteGuard supports two primary modes: mask mode, which anonymizes data and still uses external APIs; and route mode, which forwards sensitive requests to a local LLM inference engine while sending the rest to the cloud. It can be self-hosted via Docker, works with a wide range of SDKs and tools, and includes a browser extension for automatic protection in everyday AI chats. -
11
Particle Effect For UGUI
Render particle effect in UnityUI(uGUI)
...It uses Unity mesh baking APIs and CanvasRenderer instead of requiring a separate camera, render texture, or canvas. Particle effects can be sorted alongside regular UI elements by sibling order. The package supports Mask and RectMask2D components for clipping particles within interface regions. Trail modules, multiple materials, CanvasGroup alpha, and animated material properties are also supported. It works across overlay, camera-space, and world-space canvases as well as URP and HDRP rendering pipelines. -
12
SoftMaskForUGUI
Enhance Unity UI (uGUI) with advanced soft-masking features
SoftMaskForUGUI is a Unity package that adds smooth and flexible masking capabilities to the standard uGUI system. It extends traditional masks by supporting partially transparent and softened mask boundaries. Text, Image, and RawImage components can be used as masking graphics. Developers can combine multiple sprites, SpriteAtlas assets, nested masks, and ScrollRect content. The package works with overlay, camera-space, and world-space rendering and includes support for custom shaders and TextMeshPro. Performance controls, inverse masking, visible-region raycast filtering, VR support, and inspector previews provide additional control for complex interfaces. -
13
Image Harmonization Dataset iHarmony4
The first large-scale public benchmark dataset for image harmonization
...The iHarmony4 dataset comprises four sub-datasets (HCOCO, HAdobe5k, HFlickr, Hday2night), each making composite images by combining a foreground from one image with a background from another, along with associated ground truth harmonized images and foreground masks. The dataset is intended as a benchmark resource to enable and standardize research in image harmonization. Each composite sample has: composite image, foreground mask, and corresponding real harmonized image. -
14
Zelda 64: Recompiled
Static recompilation of Majora's Mask for PC
Zelda 64: Recompiled is a specialized recompilation project built on top of N64Recomp, focused on reconstructing The Legend of Zelda: Ocarina of Time and related N64 titles into native, compilable code for modern systems. It takes original game binaries and translates them into structured C code that can be compiled and run without requiring an emulator, enabling more efficient execution and deeper access to the game’s internals. The project is designed to preserve gameplay accuracy while... -
15
pg_flo
Stream, transform, and route PostgreSQL data in real-time
The easiest way to move and transform data between PostgreSQL databases. -
16
Phenaki - Pytorch
Implementation of Phenaki Video, which uses Mask GIT
Implementation of Phenaki Video, which uses Mask GIT to produce text-guided videos of up to 2 minutes in length, in Pytorch. It will also combine another technique involving a token critic for potentially even better generations. A new paper suggests that instead of relying on the predicted probabilities of each token as a measure of confidence, one can train an extra critic to decide what to iteratively mask during sampling. -
17
ControlzEx
Shared Controlz for WPF and ... more
ControlzEx is a WPF control and behavior library focused on improving desktop window experiences. It provides shared controls, helpers, and behaviors for applications that need more polished WPF interfaces. A major part of the project is its custom window chrome support, which lets developers draw inside the full window area, including the title bar. It also includes fixes and enhancements for resizing, taskbar behavior, focus visuals, tooltips, and Windows 11 window styling. The library is... -
18
Cabin
Cabin is the best JavaScript and Node.js logging service and logging
Cabin is the best JavaScript and Node.js logging service and logging npm package. Cabin is a drop-in replacement and the best alternative to Sentry, Timber, Airbrake, Papertrail, Loggly, Bugsnag, etc. Cabin will automatically detect and mask the following list of extremely sensitive types of data in your logs. Reduce your disk storage costs through Cabin's automatic conversion of Streams, Buffers, and ArrayBuffers to simplified, descriptive-only objects that otherwise would be unreadable (and obviously pollute your log files and disk storage). Cabin works with the most popular Node.js HTTP frameworks (e.g. ... -
19
SAM 2
The repository provides code for running inference with SAM 2
...SAM2 comes with pretrained weights and easy-to-use APIs, enabling developers and researchers to integrate promptable segmentation into annotation tools, vision pipelines, or downstream tasks. The project also includes scripts and notebooks to compare SAM2 against SAM on edge cases, benchmarks showing improvements, and evaluation suites to measure mask quality metrics like IoU and boundary error. -
20
VOID
Video Object and Interaction Deletion
...Unlike traditional inpainting methods that only erase pixels or simple artifacts, VOID models the full interaction dynamics between objects and their environment, including shadows, reflections, and even physical consequences such as movement or balance changes. Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. One of its most notable capabilities is its ability to simulate realistic scene behavior after object removal, such as causing an object to fall naturally if its support is removed, which significantly enhances realism. -
21
KVision
Object oriented web framework for Kotlin/JS
...Sophisticated layout containers. Forms with type safe data model and built-in validation. Different text input components including rich text, typeahead, and input mask support. Buttons, checkboxes, radios and switches. Date and time picker. Spinner and range numeric input components. Advanced select box with ajax support. File upload with preview and multi-selection. Advanced charts. Reactive tables. The navigation bar, toolbar, context menu and off-canvas sidebar. Tooltips and popovers. Modals including ready to use alerts and confirm dialogs. ... -
22
Psalm
A static analysis tool for finding errors in PHP applications
...Psalm also fixes bugs automatically, allowing you to improve your code without breaking a sweat. If Psalm cannot infer a type for an expression then it uses a mixed placeholder type. mixed types can sometimes mask bugs, so keeping track of them helps you avoid a number of common pitfalls. Psalm has a Language Server that’s compatible with a range of different IDEs. Psalm can fix many of the issues it finds automatically. -
23
Edit Banana
Edit Banana: A framework for converting statistical figures
Edit Banana is an innovative web application designed to simplify image editing by merging intuitive user interfaces with powerful generative AI capabilities, enabling users to quickly enhance, manipulate, or transform photos without needing advanced design skills. It provides a smooth, browser-based experience where users can upload images, make precise edits such as background removal or inpainting, and apply stylistic transformations or corrections through AI prompts. The tool focuses on... -
24
Sygil WebUI
Stable Diffusion web UI
Sygil WebUI is a browser-based interface for running Stable Diffusion image generation locally or on a server, wrapping common text-to-image and image-to-image workflows into a practical UI. It provides multiple UI modes (including a legacy Gradio interface) and focuses on making iterative prompting, parameter tuning, and post-processing accessible without writing code. The UI exposes core generation controls like resolution, CFG guidance, sampling steps, samplers, seeds, and batch... -
25
HunyuanVideo-Avatar
Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model
HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces,...
