Search Results for "visual"
Sort By:
Showing 535 open source projects for "visual"
View related business solutions-
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.
-
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.
-
1
1D Visual Tokenization and Generation
This repo contains the code for 1D tokenizer and generator
The 1D Visual Tokenization and Generation project from ByteDance introduces a novel “one-dimensional” tokenizer designed for images: instead of representing images with large grids of 2D tokens (as in many prior generative/image-modeling systems), it compresses images into as few as 32 discrete tokens (or more, optionally) — thereby achieving a very compact, efficient representation that drastically speeds up generation and reconstruction while retaining strong fidelity. -
2
FaceFusion
Industry leading face manipulation platform
FaceFusion is an open-source face swapping and facial enhancement toolkit designed for high-quality video and image manipulation workflows. The project enables users to replace faces in images or videos while maintaining temporal consistency and visual realism. It integrates modern deep learning models for face detection, alignment, and blending to produce smoother results than traditional approaches. FaceFusion is built with a modular pipeline that allows users to customize processing steps and optimize performance for different hardware environments. The tool is often used in content creation, visual effects experimentation, and research into generative media. ... -
3
Ren'Py
The Ren'Py Visual Novel Engine
...The engine handles essential visual novel conventions like save and load systems, rollback to previous text, scene transitions, and UI menus, so creators can focus on the story and player experience. Because it’s built on Python and widely supported across platforms, Ren’Py games can run on Windows, macOS, Linux, mobile devices, and even in browsers with HTML5 builds, helping developers reach a broad audience. -
4
Pixelle-Video
AI Fully Automated Short Video Engine
...The system emphasizes modularity, allowing developers to plug in different models or processing steps depending on the use case. It can be used for tasks such as content generation, video editing, or visual storytelling. Overall, Pixelle-Video provides a flexible environment for building AI-powered video generation and processing workflows. -
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.
-
5
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. ... -
6
Video-subtitle-remover (VSR)
AI tool that removes hardcoded subtitles and text from videos locally
...Video Subtitle Remover analyzes video frames and detects subtitle regions, then replaces the removed areas using an AI algorithm that fills the space with reconstructed visual content. This process aims to maintain the original resolution and visual continuity of the video after subtitle removal. It allows users to define a specific subtitle region so that only text in that area is removed rather than modifying the entire frame. It can also automatically remove text throughout the whole video when a position is not specified. ... -
7
ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
ComfyUI-LTXVideo is a bridge between ComfyUI’s node-based generative workflow environment and the LTX-Video multimedia processing framework, enabling creators to orchestrate complex video tasks within a visual graph paradigm. Instead of writing code to apply effects, transitions, edits, and data flows, users can assemble nodes that represent video inputs, transformations, and outputs, letting them prototype and automate video production pipelines visually. This integration empowers non-programmers and rapid-iteration teams to harness the performance of LTX-Video while maintaining the clarity and flexibility of a dataflow graph model. ... -
8
ViMax
Director, Screenwriter, Producer, and Video Generator All-in-One
ViMax is an open-source framework for performing large-scale multi-modal vision-language modeling and reasoning by combining powerful image encoders with advanced language models to solve complex visual tasks. It integrates components like visual encoders, cross-modal fusion techniques, and reasoning modules so that users can go beyond simple captioning or classification to perform tasks such as visual question answering, multi-image inference, and structured scene understanding. ViMax’s design accommodates large image sets and supports retrieval augmentation, enabling it to work with external image databases, supplementary metadata, and semantic search to enhance context awareness. ... -
9
Flowsint
Graph-based OSINT investigation platform w visual relationship mapping
Flowsint is an open source OSINT investigation platform designed to help analysts explore and understand relationships between digital entities through a visual graph interface. The platform focuses on reconnaissance and open source intelligence workflows, enabling investigators to map connections between domains, IP addresses, organizations, individuals, and other data points. By presenting these relationships in an interactive graph, Flowsint allows users to quickly identify patterns, associations, and investigative leads that might be difficult to detect through traditional data analysis methods. ... -
$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.
-
10
GalTransl
Automated translation solution for visual novels
GalTransl is an automated translation system specifically designed for visual novels, particularly those in the “galgame” genre, leveraging large language models to streamline and enhance the translation process. It integrates support for multiple advanced LLM providers such as GPT-4, Claude, DeepSeek, and other models, enabling high-quality, context-aware translations that go beyond traditional machine translation approaches. -
11
Jaaz
Open source multimodal creative AI assistant with infinite canvas tool
Jaaz is an open source multimodal creative assistant designed to help users generate and organize visual media using artificial intelligence. It functions as a creative workspace where images, videos, and visual storyboards can be produced and arranged on an infinite canvas environment. It combines AI agents with visual editing tools, allowing users to generate media through prompts, sketches, or simple instructions. Jaaz supports multiple AI models and can integrate both local and cloud-based inference systems, enabling flexible creative workflows. ... -
12
yt-dlp-gui
A cross-platform GUI wrapper for yt-dlp written in PySide6
yt-dlp-gui is a cross-platform graphical interface for the popular command-line video downloader yt-dlp, created to make video and audio downloads from sites like YouTube, Vimeo, Twitch, and others easier for everyday users without needing to work directly with command-line arguments. Written in PySide6 (Python with Qt bindings), it wraps the powerful yt-dlp engine in a visual application that lets users paste video URLs, choose formats, apply presets, and start downloads with a click, while still exposing options for advanced tweaks via configuration files. The project supports preset definitions and global arguments through a config file, so users can customize their most common download workflows—like audio extraction, quality ranking, or embedding thumbnails—without retyping arguments each time. ... -
13
AIMr
The best AI Aimbot for Fortnite, Valorant, CS2, R6, COD, Apex, & more
...The software includes various aiming enhancements, such as recoil control, silent aim, and prediction capabilities, aimed at making gameplay smoother and more competitive. AIMr also provides visual customization options like field-of-view displays and detection indicators, allowing players to tailor their interface. The system is compatible with games that use human-shaped models, and although it functions effectively out of the box, optimizing it with CUDA-accelerated OpenCV is recommended for maximum performance. -
14
InternGPT
Open source demo platform where you can easily showcase your AI models
InternGPT is an open-source multimodal AI framework designed to extend large language models beyond text interactions into visual reasoning and image manipulation tasks. The system integrates conversational AI with computer vision models so users can interact with images, videos, and visual environments through natural language instructions. Unlike traditional chat systems that rely solely on text prompts, InternGPT allows users to interact with visual content using both language and nonverbal signals such as pointing or highlighting objects within images. ... -
15
Graphify
AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw)
...The architecture emphasizes flexibility, enabling users to customize how data is mapped and displayed. It may also include analytical features to explore patterns, clusters, or anomalies within the graph. Overall, Graphify serves as a bridge between raw data and visual insight. -
16
Moondream
Tiny vision language model
...It serves as both a playground for the author’s artistic curiosity and a resource for other creative coders interested in generative art techniques. The repository may include shaders, canvas/WebGL code, visual demos, and utilities that demonstrate how mathematical functions or noise patterns can be harnessed for compelling visuals. -
17
InternLM-XComposer-2.5
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System
...It incorporates visual understanding modules that allow the model to analyze images and integrate them into coherent narrative outputs. The framework also supports tasks such as image captioning, multimodal reasoning, and layout generation for structured visual documents. By combining language generation with visual composition capabilities, the system enables new forms of content creation that integrate written explanations with automatically generated visual components. -
18
Claude How-To
A visual, example-driven guide to Claude Code
Claude How-To is a visual, example-driven guide for learning Claude Code. It covers basic concepts, memory, slash commands, hooks, skills, subagents, MCP configuration, plugins, and advanced agent workflows. The project is designed as a practical learning path rather than a simple list of notes. It includes copy-paste templates that users can apply directly to their own projects. -
19
Clarity AI Upscaler
AI Image Upscaler & Enhancer
Clarity AI Upscaler is an open-source AI image enhancement tool designed to increase the resolution and visual quality of images using modern generative techniques. The system uses deep learning models based on diffusion and other image generation methods to reconstruct high-resolution versions of low-resolution images while preserving important visual details. Unlike traditional interpolation-based upscaling algorithms, the system generates additional visual information that improves perceived clarity and sharpness. ... -
20
ComfyUI-3D-Pack
An extensive node suite that enables ComfyUI to process 3D inputs
...It incorporates modern 3D generation technologies including neural radiance fields, Gaussian splatting, and other AI-driven reconstruction techniques. Through these nodes, users can convert images into 3D models, manipulate geometry, and experiment with generative 3D workflows inside the visual pipeline editor. -
21
R1-V
Witness the aha moment of VLM with less than $3
R1-V is an initiative aimed at enhancing the generalization capabilities of Vision-Language Models (VLMs) through Reinforcement Learning in Visual Reasoning (RLVR). The project focuses on building a comprehensive framework that emphasizes algorithm enhancement, efficiency optimization, and task diversity to achieve general vision-language intelligence and visual/GUI agents. The team's long-term goal is to contribute impactful open-source research in this domain. -
22
Skywork-R1V4
Skywork-R1V is an advanced multimodal AI model series
Skywork-R1V is an open-source multimodal reasoning model designed to extend the capabilities of large language models into vision-language tasks that require complex logical reasoning. The project introduces a model architecture that transfers the reasoning abilities of advanced text-based models into visual domains so the system can interpret images and perform multi-step reasoning about them. Instead of retraining both language and vision models from scratch, the framework uses a lightweight visual projection layer that connects a pretrained vision backbone with a reasoning-capable language model. This design allows the model to analyze images while maintaining strong textual reasoning performance, enabling tasks such as solving visual math problems, interpreting scientific diagrams, and answering questions about images. -
23
SAM 3
Code for running inference and finetuning with SAM 3 model
SAM 3 (Segment Anything Model 3) is a unified foundation model for promptable segmentation in both images and videos, capable of detecting, segmenting, and tracking objects. It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short phrase or exemplars, scaling to a vastly larger set of categories than traditional closed-set models. ... -
24
WiFi DensePose
Turn WiFi signals into real-time human pose estimation and detection
...The repository includes components for data processing, model inference, and real-time visualization, making it suitable for research and experimental deployments. Its architecture emphasizes performance and reproducibility, allowing developers to explore non-visual motion capture systems using accessible hardware. Overall, WiFi DensePose functions as an advanced research-grade toolkit for WiFi-based human sensing and pose estimation. -
25
PixelRAG
The beginning of scalable pixel-native search
PixelRAG is a visual retrieval-augmented generation system that searches documents by how they look, not only by the text they contain. It renders web pages, PDFs, and images into screenshot tiles, then performs retrieval over those visual representations. This approach preserves layout, tables, charts, diagrams, infographics, and other visual structure that traditional HTML or text parsing can miss.
