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
SamurAIGPT/Generative-Media-Skills
Generative Media Skills is a collection of agent skills that give command line coding assistants, specifically Claude Code, Cursor, Gemini CLI and OpenCode, the ability to generate, edit and display images, video and audio. Every skill delegates to muapi-cli, a command line client for the muapi.ai service, so the skills themselves contain no curl calls, no JSON parsing and no boilerplate. The repository uses a core and library split so that discovery stays high-signal for an LLM. The core directory holds thin primitives for file upload, prompt-based image editing, and platform tasks such as setup, authentication and result polling. The library directory holds higher-level expert skills that translate creative intent into technical directives, including Cinema Director for film direction and cinematography, Nano-Banana for reasoning-driven image generation, UI Designer for high-fidelity mobile and web mockups following atomic design, Logo Creator for minimalist vector branding, Seedance 2 for cinematic text-to-video, image-to-video and video extension with native audio and video sync, AI Clipping which turns a long video into ranked vertical short clips with server-side transcription, virality ranking, deduplication and face-tracked auto-crop, and YouTube Shorts as a platform-aware preset over AI Clipping. On top of these sit 41 workflow recipes organised by output type, sixteen of them for motion and video, that chain several muapi-cli calls into named end-to-end pipelines such as turning a photo of a person into a 3D action figure or a product photo into a cinematic ten-second advertisement. Each recipe is a SKILL.md file the agent reads and follows rather than a bash wrapper, so a consuming agent is required. Scripts return structured JSON with semantic exit codes and support jq filtering for agentic pipelines, a --view flag downloads and opens generated media in the system viewer, and local images, videos, faces and audio are auto-uploaded to a CDN. Running muapi mcp serve exposes 19 tools to any MCP-compatible client, and more than 100 models are reachable.
https://github.com/SamurAIGPT/Generative-Media-Skills
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.
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.
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.