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
taco-group/4KAgent
4KAgent is an agentic image super-resolution system that upscales arbitrary inputs to 4K resolution regardless of image type, degradation level or domain. Instead of a single trained network, it is organised as a multi-agent pipeline. A perception agent uses a large vision-language model to analyse image content and the kinds of distortion present, then produces an explicit restoration plan. A restoration agent executes that plan step by step under an execution, reflection and rollback procedure, so a step whose output degrades quality can be reverted and retried rather than propagated. At each restoration step a quality-driven mixture-of-experts policy selects the best candidate output among several restoration tools, and a dedicated face restoration pipeline improves human faces. A profile module lets the system be reconfigured for different restoration tasks without additional training: the repository ships profiles for classic super-resolution, real-world super-resolution and other settings, selected on the command line together with the input and output directories, the VLM to use for perception, and the GPU assigned to tool execution. The authors report coverage of classical and realistic degradations, extreme low-quality inputs, AI-generated imagery, and scientific imaging including remote sensing, microscopy and biomedical data. Alongside the code the project releases DIV4K-50, a test set that asks a system to turn 256x256 low-quality images carrying multiple degradations into 4096x4096 high-quality results, published on Hugging Face. Running inference requires filling in an API key in the configuration file and installing the dependencies described in the installation guide; several restoration back-ends and vision-language models are pulled in as tools. The work comes from a group spanning Texas A&M, Stanford, Snap, Caltech, UT Austin, UC Merced and other institutions, and was accepted at NeurIPS 2025.
https://github.com/taco-group/4KAgent
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.
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.