Skills tagged: multimodal

• seedance-v2 - Seedance 2.0 Pro — Pro Pack on RunComfy

  video-generationseedanceruncomfybytedance

  ★ 0 · Updated 2026-09-21

  Generates cinematic short-form video with native lip-synced audio using ByteDance Seedance 2.0 Pro via the local RunComfy CLI.

  ⚙ Generate cinematic short-form video⚙ Synchronize native lip-synced audio⚙ Process multi-modal reference inputs
• firebase-ai-logic-basics - Integrate Firebase AI Logic into applications

  firebasegemini-apiai-logicmultimodal

  ★ 1 · Updated 2026-09-20

  Official skill for integrating Firebase AI Logic Gemini API into applications, covering setup, multimodal inference, structured output, and security.

  ⚙ Generate text responses⚙ Analyze multimodal input media⚙ Maintain multi-turn chat sessions
• firebase-ai-logic-basics - Firebase AI Logic and Gemini API integration.

  firebaseai-logicgemini-apisdk

  ★ 0 · Updated 2026-09-20

  Integrates Firebase AI Logic to call Gemini models from client SDKs for multimodal generation, streaming, and structured output.

  ⚙ Generate text responses⚙ Process multimodal input media⚙ Manage multi-turn chat sessions
• firebase-ai-logic-basics - Firebase AI Logic Integration Guide

  firebasegemini-apimultimodalai-integration

  ★ 0 · Updated 2026-09-20

  Integrates Firebase AI Logic and Gemini API into client apps for text generation, multimodal inference, streaming, and security.

  ⚙ Generate text from prompts⚙ Process multimodal input files⚙ Maintain multi-turn chat sessions
• firebase-ai-logic-basics - Integrate Firebase AI Logic into web and mobile apps

  firebasegemini-apiai-logicmultimodal

  ★ 0 · Updated 2026-09-20

  Integrates Firebase AI Logic SDK into web and mobile apps for Gemini API multimodal inference, structured output, streaming, and security configuration.

  ⚙ Generate text content⚙ Process multimodal inputs⚙ Maintain multi-turn chat sessions
• youtube-learn - Video Belief Archaeology and Multimodal Analysis

  youtubemultimodalbelief-archaeologyvideo-analysis

  ★ 29 · Updated 2026-09-20

  Extracts speaker worldviews and core beliefs from videos using multimodal frame analysis and transcripts.

  ⚙ Download video audio and frames⚙ Extract transcripts from audio⚙ Research speaker background and profile
• ai-engineer - Build production-ready LLM applications and AI agents

  aillmragagent

  ★ 0 · Updated 2026-09-19

  Develops production-ready LLM applications, advanced RAG systems, vector search, multimodal AI, and agent orchestration.

  ⚙ Build LLM applications⚙ Implement RAG systems⚙ Orchestrate multi-agent workflows
• napkin - Visual whiteboard collaboration for Copilot CLI

  whiteboardvisual-collaborationcopilot-climultimodal

  ★ 0 · Updated 2026-09-18

  Opens an interactive browser whiteboard to sketch ideas and share canvas snapshots with Copilot for visual analysis.

  ⚙ Open browser whiteboard template⚙ Read PNG canvas snapshot⚙ Read clipboard JSON data
• sd3mf-multimodal-brain-network - Supervised Deep Multimodal Matrix Factorization

  brain-networkmultimodalmatrix-factorizationconnectome

  ★ 3 · Updated 2026-09-16

  Extends SNMTF to supervised prediction over populations of multimodal graphs for interpretable brain network analysis.

  ⚙ Analyze multimodal connectome data⚙ Perform supervised prediction on graphs⚙ Extract community level interaction matrices
• ds-vision-skill - Vision extension skill for text reasoning models

  visionocrdocument-parsingrouting

  ★ 166 · Updated 2026-09-15

  Routes image, document, and OCR tasks to specialized execution tools and returns standard JSON output for text models.

  ⚙ Route vision reasoning tasks⚙ Parse document files⚙ Perform OCR text recognition
• video-analyzer - Analyze Video

  video-analysisgeminimultimodaltranscription

  ★ 97 · Updated 2026-09-12

  Analyzes a video file with Google Gemini and returns a structured markdown report covering scenes, audio transcript, visual details, and key moments.

  ⚙ Analyze video files⚙ Generate structured markdown reports⚙ Extract audio transcripts
• develop-agent-module - Develop Agent Module

  agentmoduledevelopmentdebugging

  ★ 71 · Updated 2026-06-15

  Modify, extend, or debug the agent module including graph, tools, guardrails, and wrappers

  ⚙ modify agent graph⚙ add node to agent graph⚙ modify routing
• vllm-ascend-model-adapter - Adapt models for vLLM on Ascend NPU

  Ascend NPUvLLMHugging Facemodel adaptation

  ★ 0 · Updated 2026-05-11

  Adapt and debug Hugging Face or local models for vLLM on Ascend NPU

  ⚙ collect model context⚙ analyze model files⚙ implement model adapter
• vllm-ascend-model-adapter - Adapt Models for vLLM on Ascend NPU

  vllmascendnpumodel adaptation

  ★ 2 · Updated 2026-05-11

  Adapt Hugging Face or local models to run on vllm-ascend with minimal changes

  ⚙ analyze model architecture⚙ inspect model files⚙ implement model adapter
• vllm-ascend-model-adapter - vLLM Ascend Model Adaptation

  model adaptationAscend NPUvLLMinference

  ★ 57 · Updated 2026-05-11

  Adapt and debug models for vLLM on Ascend NPU.

  ⚙ analyze model architecture⚙ implement model adapter⚙ add processor support
• ai-engineer - Build Production-Ready LLM Applications

  llmragagentsai

  ★ 11 · Updated 2026-05-09

  Build production-ready LLM applications, advanced RAG systems, and intelligent agents

  ⚙ Build LLM applications⚙ Implement RAG systems⚙ Deploy AI agents
• replay-buffer - Multimodal Experience Replay Buffer

  reinforcement learningexperience replaymultimodalmemory

  ★ 0 · Updated 2026-03-22

  Records heartbeat transitions into indexed store with sampling, time-range queries, and episode replay support.

  ⚙ record transition⚙ query buffer⚙ replay episode
• dual_branch_vit_adaptive_counter_guide - Dual-Branch ViT RGB/Event Fusion

  ViTmultimodalself_attentionPyTorch

  ★ 581 · Updated 2026-03-10

  Integrate Counter_Guide module with Adaptive_Weight into dual-branch ViT for RGB/Event fusion using Multi_Context architecture

  ⚙ implement self-attention module⚙ create multi_context attention⚙ apply adaptive weighting
• looker - Multimodal Analysis Agent for PDFs, Images, Charts and Screenshots

  multimodalanalysispdfimage

  ★ 18 · Updated 2026-03-09

  Analyzes media files including PDFs, images, charts, diagrams and screenshots to extract information

  ⚙ extract text from PDF⚙ describe image content⚙ interpret chart data
• looker - Multimodal Analysis Agent for PDF, Images, Charts and Screenshots

  multimodaldocument-analysisimage-analysisdata-extraction

  ★ 602 · Updated 2026-03-09

  Analyzes media files including PDFs, images, charts, architecture diagrams and screenshots

  ⚙ extract text from PDF⚙ describe image content⚙ interpret chart data

Scroll to load more