Search Results for "visual" - Page 7
Sort By:
Showing 471 open source projects for "visual"
View related business solutions-
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
Add Two Lines of Code. Get Full APM.Works out of the box for Rails, Django, Express, Phoenix, and more. Monitoring exceptions and performance in no time.
-
1
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. ... -
2
SteadyDancer
Harmonized and Coherent Human Image Animation
...The system can be used both in preprocessing pipelines for content creators and in live feedback loops for performers, giving dancers and videographers a tool to refine their visual outputs. It supports integration with standard video formats and includes customizable parameters so users can tune stabilization aggressiveness. -
3
Context Engineering
A frontier, first-principles handbook
...It takes inspiration from thought leaders like Andrej Karpathy and bridges theory with practical examples, offering structured guidance on context orchestration, memory, retrieval, and state control within AI workflows. With extensive materials drawn from research, surveys, and visual explanations, the project acts as both a learning resource and a reference for practitioners looking to improve model behavior by engineering richer inputs. -
4
LongCat-Image
Foundation model for image generation
LongCat-Image is an open-source foundation model for image generation and editing created by the LongCat team at Meituan, designed to deliver high-quality visual outputs while remaining efficient and accessible for developers and researchers. Rather than relying on massive parameter counts typical of many cutting-edge models, LongCat-Image achieves strong photorealism, stable structure, and accurate bilingual (Chinese and English) text rendering with a more compact ~6-billion parameter architecture, making it competitive with much larger alternatives despite its relatively lean design. ... -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
5
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion
Grounded-Segment-Anything is a research-oriented project that combines powerful open-set object detection with pixel-level segmentation and subsequent creative workflows, effectively enabling detection, segmentation, and high-level vision tasks guided by free-form text prompts. The core idea behind the project is to pair Grounding DINO — a zero-shot object detector that can locate objects described by natural language — with Segment Anything Model (SAM), which can produce detailed masks for... -
6
Wan Move
Motion-controllable Video Generation via Latent Trajectory Guidance
Wan Move is an open-source research codebase for motion-controllable video generation that focuses on enabling fine-grained control of motion within generative video models. It is designed to guide the temporal evolution of visual content by leveraging latent trajectory guidance, allowing users to manipulate how objects move over time without modifying the underlying generative architecture. By representing motion information as dense point trajectories and integrating them into the latent space of an image-to-video model, the project produces videos with more precise and controllable motion behavior than many existing methods. ... -
7
Tally
Let agents classify your bank transactions
Tally is an open-source, AI-assisted tool designed to automate the classification of personal financial transactions, helping users turn raw bank data into meaningful categories without manual tagging. At its core, Tally pairs a local rule engine with large language models so that an AI assistant (like Claude Code, Copilot, or any CLI agent) interprets, suggests, and categorizes expenses, savings, subscriptions, and income events based on your own rules and behavior. It generates... -
8
Qwen3-VL-Embedding
Multimodal embedding and reranking models built on Qwen3-VL
...The reranking model then precisely scores relevance between a given query and candidate documents, enhancing retrieval accuracy in complex multimodal tasks. Together, they support advanced information retrieval workflows such as image-text search, visual question answering (VQA), and video-text matching, while providing out-of-the-box support for more than 30 languages. -
9
zvt
Modular quant framework
...Your world is built by core concepts inside you, so it’s you. zvt world is built by core concepts inside the market, so it’s zvt. The core concept of the system is visual, and the name of the interface corresponds to it one-to-one, so it is also uniform and extensible. You can write and run the strategy in your favorite ide, and then view its related targets, factor, signal and performance on the UI. Once you are familiar with the core concepts of the system, you can apply it to any target in the market. -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
10
Material Theme
A theme for Sublime Text 3 by Mattia Astorino
This theme brings the Material Design visual language to your Sublime Text 3. If you have problems, first search for a similar issue and then report a new one. If you want to enable the white panels and inputs you can install the addon package through Package Control, search for "Material theme white panels". You have to disable it if you want to use the Lighter theme style. -
11
Diffusion for World Modeling
Learning agent trained in a diffusion world model
...Instead of interacting directly with a real environment, the reinforcement learning agent learns within a generative model that produces frames representing the environment. This approach allows training to occur in a simulated world that captures detailed visual dynamics while reducing the need for costly interactions with real environments. The system has been applied to tasks such as Atari game simulations and demonstrations involving complex environments like first-person shooter games. -
12
FireRed-Image-Edit
General-purpose image editing model that delivers high-fidelity
...It is built on a flexible text-to-image foundation model that has been extended with training paradigms including pretraining, supervised fine-tuning, and reinforcement learning to imbue the system with strong instruction following and editing consistency. The model excels in maintaining visual and text stylistic fidelity, allowing users to preserve the original artistic qualities of an image while applying creative changes according to natural language instructions. In addition to editing single images, FireRed supports multi-image editing scenarios such as virtual try-on or batch transformations, making it suitable for both creative and practical workflows. -
13
Unstract
No-code LLM Platform to launch APIs and ETL Pipelines
Unstract is a powerful open-source, no-code platform built to automate the extraction and structuring of unstructured documents using large language models and flexible workflows, enabling developers and data teams to turn messy files into organized JSON content without complex coding. It integrates a visual Prompt Studio environment where users can iteratively design extraction schemas, compare outputs from different models, and monitor costs and accuracy side by side, making it easier to refine prompts and extraction logic before deploying at scale. Unstract supports deploying structured extraction as REST API endpoints or embedding it into data engineering ETL pipelines, which allows it to plug directly into data warehouses, cloud storage, or downstream analytics systems. ... -
14
ticket
Fast, powerful, git-native ticket tracking in a single bash script
...It stores each ticket as a Markdown file with YAML frontmatter, making them human-readable and easy to version control alongside your code, while also allowing IDEs to jump straight to ticket definitions. The CLI provides common subcommands to create, list, edit, close, and manage dependencies between tickets, enabling clear hierarchical task structures and visual dependency trees. Its design is rooted in the Unix philosophy of simplicity, composability, and transparency, meaning it integrates well with other standard tools like grep, jq, and ripgrep when installed. Teams can use ticket to track bugs, features, chores, and epics with priority levels and tags, all by staying within the terminal and Git ecosystem. -
15
Oasis
Inference script for Oasis 500M
Open-Oasis provides inference code and released weights for Oasis 500M, an interactive world model that generates gameplay frames conditioned on user keyboard input. Instead of rendering a pre-built game world, the system produces the next visual state via a diffusion-transformer approach, effectively “imagining” the world response to your actions in real time. The project focuses on enabling action-conditional frame generation so developers can experiment with interactive, model-generated environments rather than static video generation alone. Because it’s an inference-focused repository, it’s especially useful as a practical reference for running the model, wiring inputs, and producing the autoregressive sequence of gameplay frames. ... -
16
Multimodal
TorchMultimodal is a PyTorch library
...The design emphasizes composability: you can mix and match encoder, fusion, and decoder components rather than starting from monolithic models. The repository also includes example scripts and datasets for common multimodal tasks (e.g. retrieval, visual question answering, grounding) so you can test and compare models end to end. Installation supports both CPU and CUDA, and the codebase is versioned, tested, and maintained. -
17
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
18
ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences
ImageReward is the first general-purpose human preference reward model (RM) designed for evaluating text-to-image generation, introduced alongside the NeurIPS 2023 paper ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation. Trained on 137k expert-annotated image pairs, ImageReward significantly outperforms existing scoring methods like CLIP, Aesthetic, and BLIP in capturing human visual preferences. It is provided as a Python package (image-reward) that enables quick scoring of generated images against textual prompts, with APIs for ranking, scoring, and filtering outputs. Beyond evaluation, ImageReward supports Reward Feedback Learning (ReFL), a method for directly fine-tuning diffusion models such as Stable Diffusion using human-preference feedback, leading to demonstrable improvements in image quality. -
19
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. ... -
20
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... -
21
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. -
22
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 simple captures, it can run custom JavaScript before taking the shot, allowing you to open menus, scroll, or manipulate the DOM so the screenshot reflects the desired state. ... -
23
Luigi
Python module that helps you build complex pipelines of batch jobs
Luigi is a Python (3.6, 3.7, 3.8, 3.9 tested) package that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization, handling failures, command line integration, and much more. The purpose of Luigi is to address all the plumbing typically associated with long-running batch processes. You want to chain many tasks, automate them, and failures will happen. These tasks can be anything, but are typically long running things like Hadoop... -
24
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a... -
25
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...
