
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX expo
- Open source
- 4K GitHub stars
- Design and media

InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX expo

Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint

"Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them

"Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region

Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API

Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket


Azure AI Voice Live SDK for .NET

Azure AI Content Safety SDK for Python

Azure AI Content Understanding SDK for Python

Azure AI Transcription SDK for Python

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive)

Azure Speech to Text REST API for short audio (Python)

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety)

Azure AI Voice Live SDK for JavaScript/TypeScript

When the user wants to plan, script, produce, or optimize App Store Preview videos or Google Play promo videos — the autoplay videos that sh

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI

Make a showreel-grade product film (landing-page loop, launch video, promo, demo reel, social cut) in code with Remotion, built on the produ

Rebuilds an AI-generated (or any) flat motion design video as clean, editable code: inline SVG shapes animated by one GSAP timeline, seekabl

Makes and fixes 3D assets in Blender, for games, the web and AR

Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and s

Define how system components connect, establishing boundaries, patterns, and integration approaches during PRD v0.6 Architecture

Use this skill to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), ei

Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/r

Extract and summarize YouTube video content via subtitle extraction

Build polished product launch videos in Remotion from brief → storyboard → render → multi-agent review → iterate

YouTube Marketing MCP — 21-command suite for YouTube creators

Improves the quality of images, especially screenshots, by enhancing

Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime wi