Search Results for "visual code" - Page 5
Sort By:
340 projects for "visual code" with 1 filter applied:
-
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.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and... -
2
GPTImage2Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
...It provides reusable image prompts across creative, technical, academic, interface, design, photography, typography, gaming, anime, map, tattoo, and reference-editing use cases. The project is designed to help agents and users produce stronger visual outputs without starting from a blank prompt every time. Its gallery is organized into category files so an agent can load only the relevant prompt references instead of overwhelming the context window. It also includes installation paths for skill-capable environments such as Claude Code, Codex, OpenClaw, and other agent runtimes. ... -
3
skycaiji
Open source web scraping system for automated data collection tasks
SkyCaiji is an open source web scraping and data collection system designed to gather information from websites through configurable extraction rules. It focuses on simplifying the process of building crawlers by allowing users to visually define scraping rules rather than writing complex code. It can collect structured or unstructured data from many types of webpages and automate the extraction process for large datasets. SkyCaiji is designed to run on a variety of hosting environments... -
4
dots.ocr
Multilingual Document Layout Parsing in a Single Vision-Language Model
...It achieves state-of-the-art performance on document parsing benchmarks while maintaining a relatively compact model size, demonstrating efficiency without sacrificing accuracy. Beyond standard OCR tasks, it extends its capabilities to parse complex visual elements such as charts, diagrams, and web interfaces, converting them into structured outputs like SVG code. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
MiniMind-V
"Big Model" trains a visual multimodal VLM with 26M parameters
MiniMind-V is an experimental open-source project that aims to train a very small multimodal vision–language model (VLM) from scratch with extremely low compute and cost, making research and experimentation accessible to more people. The repository showcases training workflows and code designed to produce a 26-million parameter model—including both image and text capabilities—using minimal resources in very little time, reflecting a trend toward democratizing AI research. MiniMind-V combines... -
6
Magazine Web PPT
A Claude Code Skill that turns prompts into magazine-style HTML decks
Magazine Web PPT is a specialized AI skill set designed to enhance the creation and structuring of PowerPoint presentations. It provides guidance on slide organization, storytelling, and visual design principles tailored for professional presentations. The system helps users transform raw ideas into coherent slide decks with clear messaging and logical flow. It emphasizes effective communication through structured layouts and concise content. The project is particularly useful for business,... -
7
dockview
Zero dependency docking layout manager supporting tabs
dockview is a zero-dependency docking layout manager written in TypeScript that enables developers to create highly dynamic, IDE-like interfaces with draggable panels, tabs, and resizable layouts. It supports multiple layout paradigms, including split views, grid layouts, and dockable panels, allowing complex UI arrangements similar to tools like Visual Studio Code. The library is framework-agnostic at its core, with official bindings for React, Vue, and Angular, as well as support for vanilla TypeScript. Dockview includes advanced features such as floating panels, popout windows, and persistent layout serialization, enabling users to save and restore custom workspace configurations. ... -
8
scroll-world
A skill that turn any brand into a scrollable 3D world
Scroll World is an agent skill for producing immersive landing pages that feel like one continuous camera flight through a generated 3D world. It works with Claude Code, Codex, and other systems that support the SKILL.md format. The workflow interviews the user about the brand, message, visual direction, and ordered sequence of scenes. It then uses Higgsfield to generate still images, scene-entry videos, and connector clips built from matching boundary frames. A portable JavaScript engine maps scrolling to video time, adds lazy loading, and blends seams between clips. ... -
9
Exclusively Dark Image Dataset
ExDARK dataset is the largest collection of low-light images
...It has been widely used in studies of low-light image enhancement, deep learning approaches, and domain adaptation for vision models. Researchers can also explore its associated source code for low-light image enhancement tasks, making it an essential resource for advancing work in night-time and low-light visual recognition. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Magic Portfolio
Build your timeless portfolio with Once UI's Magic Portfolio
Magic Portfolio is a Next.js-based portfolio template built on the Once UI design system, designed to give developers and creatives a clean, timeless way to showcase their work. It provides a minimal, beginner-friendly setup that focuses on strong typography, responsive layouts, and restrained motion instead of heavy animations. Content is managed through a structured configuration and MDX-based content system, so you can define sections, projects, blog posts, gallery items, and about/CV... -
11
Sera UI
UI component library for React, Next.js, and other JSX frameworks
Sera UI is a modern, open source component library designed for React, Next.js, and other JSX-based frameworks, focused on helping developers build visually polished and highly interactive user interfaces with minimal effort. It is built on top of Tailwind CSS, which enables a utility-first styling approach that makes customization fast, flexible, and consistent across projects. One of its defining characteristics is its copy-and-paste philosophy, allowing developers to directly own and... -
12
MGIE
Guiding Instruction-based Image Editing via Multimodal Large Language
MGIE—Guiding Instruction-based Image Editing—demonstrates how a multimodal LLM can parse natural-language editing instructions and then drive image transformations accordingly. The project focuses on making edits explainable and controllable: the model interprets text guidance, reasons over image content, and outputs edits aligned with user intent. It’s positioned as an ICLR 2024 Spotlight work, with code and references that show how to connect language planning to concrete image operations.... -
13
Padrões de commits
Reference project for creating clear, standardized Git commit messages
Padrões de Commits is a reference project for creating clear, standardized Git commit messages. It explains semantic commit conventions and how structured messages make project history easier to understand and automate. The guide covers common types such as feat, fix, docs, test, build, perf, style, refactor, chore, and ci. It pairs many commit categories with emojis for quick visual identification. The repository also includes a commit-msg shell hook that can validate messages against... -
14
Upscale-A-Video
Temporal-Consistent Diffusion Model for Real-World Video
...The model is designed for real-world videos where compression artifacts, blur, aging, or generated-video defects can make ordinary upscaling less reliable. The repository includes inference code, example inputs, configuration structure, pretrained model instructions, and optional LLaVA-assisted prompt support. It includes example workflows for AIGC videos, old videos, movies, and animations. It also provides color correction options to help reduce visual mismatch between the input and enhanced output. -
15
gzh-design-skill
An AI-agent skill that turns Markdown into paste-ready WeChat article
gzh-design-skill is an AI-agent workflow that converts Markdown into polished HTML for the WeChat Official Account editor. It uses fully inline styling and platform-aware markup so pasted articles retain their formatting after WeChat filters the content. The skill recognizes headings, quotations, lists, code blocks, images, highlights, and other Markdown structures before assembling them from reusable components. Six built-in themes cover tutorials, reviews, essays, reports, technology... -
16
Gitlogue
A cinematic Git commit replay tool for the terminal
Gitlogue provides a fun and creative command-line tool that turns your Git commit history into an animated replay, displaying your commits as if someone were typing the changes in real time with cinematic flair. When you run this tool in the terminal, it visually replays diffs line by line, highlights syntax, and shows changes evolving in a way that feels like watching a code story unfold, which can be entertaining and useful for reviewing history or showcasing progress. It builds on typical Git data but reshapes it into a compelling narrative with visual appeal, making it great for demos, teaching, or just savoring your development journey. The tool is standalone and designed to be easy to install and run, so users don’t need complex setups to enjoy animated commit histories. ... -
17
Codex Skill Manager
macOS app to manage your Codex skills
CodexSkillManager is a native macOS application built with SwiftUI that provides a visual and user-friendly interface for managing local skills used by AI coding assistants like Codex and Claude Code. It allows users to browse, install, delete, and inspect both locally stored and remote skills (such as those from Clawdhub) without requiring manual file manipulation on disk, making it simpler to keep skills organized and up to date. -
18
ClawPort
Open-source AI agent command center for Claude Code agent teams
ClawPort is an open-source web-based dashboard designed to act as a centralized command center for managing and interacting with OpenClaw AI agent systems. It provides a visual interface that replaces fragmented terminal-based workflows, allowing users to monitor, control, and communicate with multiple agents from a single location. The platform is built to improve visibility into multi-agent environments, offering insights into agent activity, task execution, and system performance in real... -
19
Next.js Landing Page Starter Template
Free NextJS Landing Page Template written in Tailwind CSS 3
...SEO support includes metadata, Open Graph information, and JSON-LD structured data. Developer tooling combines ESLint, Prettier, Husky, lint-staged, PostCSS, and prepared Visual Studio Code settings. Static generation, minification, live reload, cache busting, and unused CSS removal help produce efficient deployments. The project can be hosted through Netlify or exported for another static hosting service. -
20
SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow
...The project focuses on converting images of handwritten text into machine-readable digital text using neural networks. The system uses a combination of convolutional neural networks and recurrent neural networks to extract visual features and model sequential character patterns in handwriting. It also employs connectionist temporal classification (CTC) to align predicted character sequences with input images without requiring character-level segmentation. The repository provides code for training models, performing inference on handwritten text images, and evaluating recognition accuracy. ... -
21
JobWinner
Curated directory of thousands of generative AI tools by category
AI Collection is a curated repository that aggregates a large number of generative AI applications into a single organized directory. It serves as a discovery platform where users can browse and explore AI tools across a wide range of categories and use cases. Instead of providing software code for a single application, AI Collection acts as a structured index that lists AI tools along with brief descriptions and visual previews. It organizes thousands of AI applications into dozens of categories, allowing users to easily locate tools related to areas such as image generation, writing assistance, chatbots, productivity, and automation. ... -
22
APNGKit
High performance and delightful way to play with APNG format in iOS
The APNGKit project is a high-performance framework for loading, displaying, and animating images in the UIKit / AppKit ecosystem (iOS, macOS, tvOS), specifically targeting the APNG (Animated PNG) image format. Unlike traditional static PNG images, APNG supports frame-by-frame animation with full-color images and transparency — yielding better visual fidelity than GIFs while remaining efficient. APNGKit offers a friendly API (e.g. APNGImage, APNGImageView) that behaves similarly to the... -
23
shot-scraper
A command-line utility for taking automated screenshots of websites
shot-scraper is a command-line utility for taking automated screenshots of web pages using a headless browser engine. After installation, a single command can capture a full-page screenshot of a URL and save it to a file, making it ideal for documentation, monitoring, and visual regression tasks. Under the hood it uses a modern browser (installed via a one-time shot-scraper install step) and exposes options for viewport size, full-page versus clipped screenshots, and device emulation. Beyond... -
24
_s
Inactive project
Underscores is a no-frills WordPress starter theme engineered to give developers a clean, standards-based foundation for building custom themes. It provides semantic templates, accessibility-minded markup, and a minimal stylesheet that sets sensible defaults without imposing a visual identity. The codebase includes template tags, custom header and menu scaffolding, widget areas, and translation-ready strings to speed up common theme tasks. Its structure is intentionally opinionated about where code lives and how templates compose, which makes large customizations predictable and maintainable. Developers can opt into Sass and build helpers, but the theme is usable as a lightweight baseline even without a complex toolchain. ... -
25
ThreeUI Community
Open-source ThreeUI Community catalog with live interactive components
ThreeUI Community is the open-source, login-free edition of the ThreeUI interactive component library. It provides dozens of visual components and more than one hundred routes with free variants and controls. The application includes the same navigation, browse grid, search, responsive layouts, themes, component pages, live renderers, and source tabs used by the broader ThreeUI experience. Developers can browse components interactively and inspect their complete Community implementation...
