Qwen2.5-VL ↗
用途介绍 图像与视频理解模型
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
QwenLM/Qwen2.5-VL
GitHub ★ 20176 · 仓库更新 2026-01-30
许可 · Apache-2.0 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →收集图片提示词、导演 Skill、工作流、技术教程与开源项目,串联创意与内容制作。
1380 项资源 · 提示词集 101 · 工作流 242 · Skill 281 · 教程 134 · 项目 622
链接核验记录用于确认资源可访问。安装运行与商用授权请以项目文档、代码和模型许可证为准。
匹配 209 项 · 第 6 / 6 页
用途介绍 图像与视频理解模型
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
QwenLM/Qwen2.5-VL
GitHub ★ 20176 · 仓库更新 2026-01-30
许可 · Apache-2.0 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 端侧与高效视觉语言模型
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
OpenBMB/MiniCPM-V
GitHub ★ 27087 · 仓库更新 2026-10-30
许可 · Apache-2.0 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 图文识别和文档解析
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
PaddlePaddle/PaddleOCR
GitHub ★ 92419 · 仓库更新 2026-09-16
许可 · Apache-2.0 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 多模态理解与图像生成
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
deepseek-ai/Janus
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 视觉文本识别与文档处理
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
deepseek-ai/DeepSeek-OCR
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 视觉语言模型与多模态应用
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
OpenGVLab/InternVL
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 视频与图像的多模态理解
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
PKU-YuanGroup/Video-LLaVA
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 音乐与歌曲生成
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
multimodal-art-projection/YuE
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-enco
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
huggingface/skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
huggingface/skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
huggingface/skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Call the Gemini API from the shell with gemini-api. Use for media generation (images, TTS, music, video), file and YouTube analysis, audio/video transcription, Deep Research, and sandboxed agents.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
google-gemini/gemini-skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Use this skill for generative video editing, text-to-video, image-referenced video generation, first-frame-to-video, first-and-last-frame transitions, and video extensions using Gemini Omni 1.1 Flash (gemini-omni-1.1-flash) via the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound regeneration, and handling turn-by-turn video editing and parallel execution.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
google-gemini/gemini-skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), background reasoning (extended thinking), asynchronous function calling, session management, ephemeral tokens, live transcription, and live translation. SDKs covered - google-genai (Python), @google/genai (JavaScript/TypeScript).
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
google-gemini/gemini-skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best practices for Gemini models and agents in Python and TypeScript.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
google-gemini/gemini-skills
许可 · 查阅原站许可 · 核验 2026-11-18
收录 2026/11/8
查看原始资源 →用途介绍 语言和多模态模型的推理服务
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
sgl-project/sglang
GitHub ★ 38830 · 仓库更新 2026-11-13
许可 · Apache-2.0 · 核验 2026-11-18
查看原始资源 →用途介绍 语言、视觉与多模态模型工具库
前置条件 · 按 README 配置运行环境、模型或服务;模型与依赖许可需分别核对
huggingface/transformers
GitHub ★ 168951 · 仓库更新 2026-11-13
许可 · Apache-2.0 · 核验 2026-11-18
查看原始资源 →用途介绍 Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image", "make a video", "text to 3D", or ComfyUI workflow task.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
Comfy-Org/comfy-skills
GitHub ★ 247 · 仓库更新 2026-10-23
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Build a fully-interactive 3D character-selector experience powered entirely by fal.ai. Generates stylized characters (FLUX.2 / GPT-Image-2), rigged animated GLBs (Meshy v6), themed companion creatures, per-character PATINA floor textures, looped Seedance video backgrounds, and a Three.js scene with palette swaps, breathing reflections, transition effects and a CREATE-YOUR-OWN flow.
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Decides whether a specific image use is legally permitted, what the license obligates, and whether a model or property release is required - covering CC0 and Creative Commons variants, Unsplash/Pexels/Pixabay terms, royalty-free vs rights-managed, standard vs extended tiers, editorial-use-only, and AI-image caveats - and delivers a per-image license record. Use when someone asks "is this free for commercial use", "do I need to credit the photographer", "can I put this on merchandise", "what is royalty-free vs rights-managed", "is editorial-use-only a problem", or "do I need a model release", or is about to publish, advertise, or sell anything
前置条件 · 支持 Agent Skill 的助手;按原文准备工具和服务,部分生成接口按用量计费
SkillMedev/skills
GitHub ★ 24 · 仓库更新 2026-10-13
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 项目官方技术文档,介绍多模态图文理解的操作步骤与配置方式。
前置条件 · 按原文档准备对应工具、模型和运行环境
huggingface/transformers
GitHub ★ 168951 · 仓库更新 2026-11-13
许可 · Apache-2.0 · 核验 2026-11-18
查看原始资源 →用途介绍 Produce fal voiceover, dubbing, speech transcription, sound effects or music. Use for audio deliverables, a pinned project voice and timing checks.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Generate or process media with connected fal MCP tools. Use for Fal model selection, schemas, pricing, uploads and job recovery; preserve an explicitly chosen…
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Render animated titles, lower thirds, logo cards and captions over video. Use for deterministic text and logo motion with a verified local renderer.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Write timed scripts and shot tables for short films or ads. Use for story beats, voiceover budgets and continuity notes; this skill makes no…
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Write or improve one fal video shot prompt. Use for physical action, motivated cameras and continuity anchors; do not use for full film assembly.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Generate or transform a fal video clip. Use for image animation, reference video, extension, restyling or upscaling; use storyboard-to-short-film for a complete cut.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Coordinate fal short-ad production with per-shot picture, voice, music and final quality checks. Use when a finished ad with audio is requested.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →用途介绍 Assemble footage, captions, graphics and audio into a rendered video. Use when the required renderer is available; check host prerequisites before execution.
前置条件 · 支持 Agent Skill 的助手及技能所需的生成服务
fal-ai-community/skills
GitHub ★ 264 · 仓库更新 2026-11-07
许可 · MIT · 核验 2026-11-18
查看原始资源 →浏览网站正在采集的教程、工具与项目发布,按需补充到制作流程。
教程实践 → 创作工具 →