img2threejs/img2threejs
Agent skill for Claude Code and Codex that rebuilds the object in a reference image as procedural Three.js TypeScript code through a gated, vision-reviewed, token-efficient pipeline.
Awesome AI Agents › Image Processing & Analysis Agents
QIN2DIM/hcaptcha-challenger
hCaptcha Challenger is an advanced project designed to tackle hCaptcha challenges using a multimodal large language model approach. Unlike traditional methods, it does not rely on Tampermonkey scripts or third-party anti-captcha services, instead implementing interfaces that enable an AI versus AI interaction to solve these challenges. The project supports various types of hCaptcha challenges, including image label binary classification, area selection with points or bounding boxes, multiple-choice image labeling, and image drag-and-drop tasks. It leverages state-of-the-art machine learning models such as ResNet, YOLOv8, and ViT in ONNX format to handle these tasks effectively. The project is structured to allow pluggable resources for different challenge types, enabling flexibility and extensibility. For example, ResNet is used for binary image classification, YOLOv8 for object detection and segmentation, and ViT for zero-shot motion recognition. Additionally, it incorporates advanced tasks like ranking strategies, self-supervised challenges using CLIP-ViT, and agentic workflows powered by AIOps multimodal large language models. The workflow of the project includes continuous integration tasks such as sentinel and collector jobs, dataset version control and annotation through platforms like Roboflow, and model training and validation using Colab notebooks. Models are regularly uploaded and upgraded, with datasets publicly archived for transparency and community use. The project is actively maintained with contributions from a diverse group of developers and provides multilingual documentation in English, Simplified Chinese, Russian, and Vietnamese. It also integrates with other related projects and tools, such as Discord Browser Generator, undetected-playwright for web agent fingerprinting, and Epic Store game claimers. Overall, hCaptcha Challenger represents a sophisticated and modular AI-driven solution for automating the solving of hCaptcha challenges, emphasizing open-source collaboration, advanced machine learning techniques, and practical application workflows.
https://github.com/QIN2DIM/hcaptcha-challenger
Also in Image Processing & Analysis Agents
apple/ml-ferret
Ferret is an end-to-end multimodal large language model developed by Apple that excels in fine-grained referring and grounding tasks with open vocabulary, supported by a large-scale dataset and evaluation benchmark for research purposes.
THUDM/CogVLM
CogVLM and CogAgent are state-of-the-art open-source visual language models designed for advanced image understanding, multi-turn dialogue, and GUI agent capabilities, achieving top performance on multiple cross-modal benchmarks.
11cafe/jaaz
Jaaz is a local and free AI design agent that enables users to design, edit, and generate images, posters, and storyboards with advanced AI-powered tools and a creative canvas for fast iterations.
SamurAIGPT/Generative-Media-Skills
Collection of agent skills and workflow recipes giving Claude Code, Cursor, Gemini CLI and OpenCode access to image, video and audio generation models through muapi-cli and an MCP server.
roboflow/inference
Roboflow Inference is a platform that turns any computer or edge device into a command center for deploying and managing computer vision models and workflows, enabling advanced AI-powered visual applications.
mbzuai-oryx/groundingLMM
GLaMM is a groundbreaking multimodal AI model that generates natural language responses integrated with object segmentation masks, enabling advanced visual grounding and conversational tasks.
LYL1015/JarvisArt
Research release of an intelligent photo retouching agent built on a multimodal LLM that plans edits from natural language and drives Adobe Lightroom through a dedicated agent protocol.