Search Results for "image processing framework" - Page 6
Sort By:
736 projects for "image processing framework" with 1 filter applied:
-
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
Open Vision Agents by Stream
Build Vision Agents quickly with any model or video provider
Open Vision Agents by Stream is an open source framework from Stream for building real time, multimodal AI agents that watch, listen, and respond to live video streams. It focuses on combining video understanding models, such as YOLO and Roboflow based detectors, with real time large language models like OpenAI Realtime and Gemini Live to create interactive experiences. The framework uses Stream’s ultra low latency edge network so agents can join sessions quickly and maintain very low audio and video latency while processing frames and generating responses. ... -
2
HY-World 2.0
A Multi-Modal World Model for Reconstructing, Generating, Simulation
HY-World 2.0 is a multi-modal world model framework for reconstructing, generating, and simulating navigable 3D worlds from diverse inputs. It accepts text prompts, single-view images, multi-view images, and videos, and produces 3D world representations rather than limiting output to flat video generation. For text and single-image inputs, it generates high-fidelity 3D Gaussian Splatting scenes through a multi-stage pipeline that includes panorama generation, trajectory planning, world expansion, and world composition. ... -
3
Open Multi-Agent
One runTeam() call from goal to result
...The architecture is designed to be extensible, enabling integration with external tools and APIs to expand agent capabilities. It is particularly useful for research, automation, and development workflows that require multiple perspectives or stages of processing. Overall, open-multi-agent provides a foundation for building scalable and cooperative AI systems. -
4
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... -
$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.
-
5
Roadmap To Learn Generative AI In 2025
Basic Machine Learning Natural Language Processing Roadmap
Roadmap To Learn Generative AI In 2025 is a curated learning path focused on contemporary generative AI — covering large language models (LLMs), diffusion-based image generation, prompt engineering, multi-modal AI, fine-tuning techniques, and the practical considerations for deploying generative models. It’s aimed at learners and developers who already have some programming or ML basics and wish to specialize in generative AI, offering a modern, structured plan that reflects the state of the... -
6
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... -
7
mergekit
Tools for merging pretrained large language models
...The library is designed to operate efficiently even in environments with limited hardware resources by using memory-efficient processing methods that can run entirely on CPUs. It also provides configuration-driven workflows that allow users to experiment with different merging strategies without modifying source code. -
8
jSuites
Collection of lightweight common required javascript web components
...It includes a broad set of components such as calendars, dropdowns, color pickers, modals, sliders, tags, input masks, context menus, and rich form utilities that help enhance user experience without reinventing the wheel for each project. These components are framework-agnostic, meaning they can be used with plain JavaScript or easily integrated into major frameworks like React, Angular, and Vue, giving developers flexibility in how they adopt them. The suite also offers extended plugins for specialized needs like image cropping, heatmaps, and organograms, broadening its utility for diverse use cases. -
9
OPENRNDR
Kotlin library for creative coding, real-time and interactive graphics
OPENRNDR is an open source framework for creative coding, written in Kotlin that simplifies writing real-time interactive software. OPENRNDR provides simple, reusable utilities with which creative coders can build robust, fast, and reliable (interactive) applications for prototyping as well as building production-quality software. With ORML you can easily connect to a number of widely used Machine Learning models, such as Facemesh, Posenet, and Stylegan. You can use OPENRNDR to visualize the... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
FISSURE
The RF and reverse engineering framework for everyone
...The platform supports workflows related to signal discovery, demodulation, packet inspection, fuzzing, and attack simulation, making it useful for both defensive research and controlled lab testing. Its architecture is oriented toward extensibility, so users can integrate additional hardware, signal-processing components, and protocol-specific modules depending on their needs. -
11
QueryList
Progressive PHP web crawler framework with jQuery-like DOM parsing
QueryList is an extensible PHP web scraping and crawling framework designed to extract and process data from web pages. It provides a simple and expressive API that allows developers to collect structured information from HTML documents using familiar DOM traversal techniques. It is built on top of phpQuery and uses CSS3 selectors similar to those found in jQuery, making it easy for developers to query and manipulate page elements during scraping tasks. QueryList supports common data... -
12
ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
ModernBERT is an open-source research project that modernizes the classic BERT encoder architecture by incorporating recent advances in transformer design, training techniques, and efficiency improvements. The goal of the project is to bring BERT-style models up to date with the capabilities of modern large language models while preserving the strengths of bidirectional encoder architectures used for tasks such as classification, retrieval, and semantic search. ModernBERT introduces... -
13
Agent SOP
Natural language workflows for AI agents
...It defines reusable SOP templates that agents can instantiate with context-specific parameters, allowing organizations to codify best practices for customer support, data processing, document workflows, or incident response. The framework supports monitoring and state tracking, so external systems can observe progress, intervene if necessary, and log outcomes for compliance or auditing. Integrations with common messaging and task orchestration systems enable SOP agents to interact with email, ticket queues, and databases as part of their workflows. -
14
FlowGram
Extensible workflow development framework
...This makes FlowGram highly flexible: you can prototype data-processing pipelines, AI-agent flows, automation scripts, or even business process automation without writing all the plumbing yourself. The framework supports both free-layout canvases (for free-form graphs) and fixed-layout canvases (for more structured flowcharts, including loops, branches, compound nodes), giving you visual freedom depending on your use-case. -
15
Google Research
This repository contains code released by Google Research
Google Research is a massive monorepo that hosts a wide range of research code released by Google Research teams across machine learning, artificial intelligence, robotics, natural language processing, and other advanced domains. Rather than being a single framework, the repository serves as a centralized collection of experimental projects, reference implementations, and reproducible research artifacts. It is intended primarily for researchers and advanced practitioners who want to explore cutting-edge techniques directly from the teams that developed them. ... -
16
Perfect Pixel
Refine and quantize messy AI pixel art into clean, perfect pixels
...It tackles a common problem with AI pixel art: edges that look pixelated at first glance but are not actually aligned to a coherent pixel grid, which causes shimmer, blur, and uneven block sizes when you zoom in. The tool analyzes an image to infer the intended grid size, then refines and quantizes the artwork so pixels snap into consistent cells and the final result looks crisp and intentional. This makes it useful for game developers, sprite artists, and hobbyists who want to use AI-assisted ideation without shipping “almost pixel art” assets. It is designed to be easy to slot into an existing pipeline, whether you are batch-processing images or cleaning up a few key assets for a project. -
17
Slambook2
edition 2 of the slambook
...The repository teaches the mathematical and programming foundations required to understand visual SLAM implementations. Its C++ exercises cover geometry, Lie theory, cameras, image processing, optimization, visual odometry, mapping, and loop closure. Chapter folders let readers study individual techniques before connecting them into broader localization and mapping pipelines. Supplemental files include errata, exercise solutions, notes, figures, and small demonstrations of matrix and coordinate operations. ... -
18
JoyAI-Echo
Pushing the Frontier of Long Audio-Visual Generation
...JoyAI-Echo focuses on text-to-video and multi-shot long-video generation, while image-to-video support is not part of the current release scope. It is most useful for research and experimental video workflows that need synchronized audio, coherent characters, and editable story-level generation. -
19
Matrix
Multi-Agent daTa geneRation Infra and eXperimentation framework
Matrix is a distributed, large-scale engine for multi-agent synthetic data generation and experiments: it provides the infrastructure to run thousands of “agentic” workflows concurrently (e.g. multiple LLMs interacting, reasoning, generating content, data-processing pipelines) by leveraging distributed computing (like Ray + cluster management). The idea is to treat data generation as a “data-to-data” transformation: each input item defines a task, and the runtime orchestrates asynchronous,... -
20
weixin-agent-sdk
Bridging framework for connecting arbitrary AI agents
Weixin Agent SDK is an unofficial bridging framework for connecting arbitrary AI agents to Weixin through a simple programming interface. Developers implement an Agent interface that receives conversation identifiers, text, and optional media and returns text or media responses. An included ACP adapter can connect compatible agents such as Claude Code, Codex, and other command-line agents without custom integration code. QR-code login handles account authentication, while a message loop... -
21
Lyra 2
Project Lyra: Open Generative 3D World Models
The Lyra 2 project is a research-driven framework developed by NVIDIA that focuses on building open generative 3D world models using advanced diffusion-based techniques. It enables the creation of fully explorable 3D environments from minimal inputs such as a single image or video, leveraging self-distillation methods to generate consistent spatial representations. The system evolves across versions, with newer iterations introducing long-horizon generation and improved 3D consistency across frames. ... -
22
Rig
Rust framework for building modular and scalable LLM-powered apps
Rig is an open source Rust framework designed to help developers build modular and scalable applications powered by large language models. It provides a unified set of abstractions that allow applications to interact with many AI model providers and vector databases through a single interface. Its architecture emphasizes modularity, enabling developers to integrate only the components and integrations they need for a specific application. -
23
RuleGo
Component orchestration rule engine framework for Go
RuleGo is a high-performance, component-based rule engine implemented in Go. It’s lightweight, embeddable, orchestration-ready, and built for flexible composition of business logic into reusable components. No external middleware dependencies, efficient data processing and linkage on low-cost devices, suitable for IoT edge computing. Embedded and Standalone Deployment modes. Supports embedding RuleGo into existing applications. It can also be deployed independently as middleware, providing... -
24
Compose Destinations
Annotation processing library for type-safe Jetpack Compose navigation
A KSP library that processes annotations and generates code that uses Official Jetpack Compose Navigation under the hood. It hides the complex, non-type-safe and boilerplate code you would have to write otherwise. No need to learn a whole new framework to navigate - most APIs are either the same as with the Jetpack Components or inspired by them. -
25
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations.
