★ 147,207 · Python|The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
★ 81,045 · Python|World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
★ 79,625 · Python|Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
★ 50,395 · Go|LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
★ 144,042 · Python|利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
★ 107,958 · TypeScript|The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate…
★ 46,492 · TypeScript|Interoperable by design. Governed by you. Open-source, secure platform for messaging, voice, video and governed AI, built for defense and government.
Trending 442 · ♥ 12,263 · ↓ 2,789,021|diffusion-single-file, image-to-video, text-to-video, video-to-video
Q1:目前 AI 圖片與影片生成最主流的開源工作流是什麼?
圖片領域以 Flux 與 ComfyUI 模組化節點為主流;影片生成則以 Hugging Face 熱門開源模型(如 Wan、HunyuanVideo、LTX)搭配短影音剪輯自動化工具最受創作者青睞。
Q2:開發者都在追哪些 AI Agent 新標準?
GitHub 與開發社群目前高度聚焦於 MCP(Model Context Protocol)、可重複呼叫的 AI Skill 與多代理(Multi-Agent)自動化框架,能直接串接本地資料與外部 API。
Q3:在哪裡可以持續追蹤這些國內外工具與新聞?
歡迎鎖定 PiNews 拍新聞 每日科技情報專欄,掌握最新 AI 工具、開源專案與台灣產業動態。