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
mbzuai-oryx/groundingLMM
Grounding Large Multimodal Model (GLaMM) is a pioneering AI model introduced at CVPR 2024 that integrates natural language processing with visual grounding capabilities. It is designed to generate natural language responses that are seamlessly combined with object segmentation masks, enabling a new unified task called Grounded Conversation Generation (GCG). This task merges phrase grounding, referring expression segmentation, and vision-language conversations, allowing the model to understand and interact with visual inputs at multiple levels of granularity, including image-level and region-level inputs. GLaMM is trained end-to-end and is capable of detailed region understanding and pixel-level grounding, making it highly versatile for various applications involving visual and textual data. The project includes the creation of the GranD dataset, a large-scale, densely annotated dataset with 7.5 million unique concepts grounded in 810 million regions, each annotated with segmentation masks. This dataset supports the training and evaluation of GLaMM and related tasks. The project provides comprehensive resources including training and evaluation codes, pretrained checkpoints, and an automated annotation pipeline for the GranD dataset. It also offers an online interactive demo and detailed documentation covering installation, dataset preparation, model training, evaluation, and demo setup. GLaMM supports several downstream applications such as referring expression segmentation, region-level captioning, and image captioning, demonstrating competitive performance compared to specialized models. It also extends to conversational style question answering, enhancing interactive AI capabilities with grounded visual context. Overall, GLaMM represents a significant advancement in multimodal AI, combining language and vision in a unified framework that supports complex visual grounding and conversational tasks, backed by a large-scale dataset and extensive tooling for research and application development.
https://github.com/mbzuai-oryx/groundingLMM
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.
QIN2DIM/hcaptcha-challenger
hCaptcha Challenger is an open-source project that uses multimodal large language models and advanced machine learning techniques to automate solving hCaptcha challenges without relying on third-party services or scripts.
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.
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.