chatfire-AI/huobao-canvas

火宝无限画布；支持文生图，图生图，图生视频，多模型切换。兼容 openai标准格式

What it solves

Huobao Canvas provides a visual, node-based interface for creating AI-driven content. It eliminates the need to switch between different AI tools and platforms by allowing users to chain together text, image, and video models from multiple providers on a single infinite canvas, turning a complex sequence of AI generations into a visible production pipeline.

How it works

Users place different types of nodes (text, image, video, or group) on a canvas and connect them using "wires." The output of an upstream node automatically flows into the downstream node as an input. For example, a text node can feed into an image node, which then feeds into a video node. The system includes native adapters for 11 different AI providers, allowing users to plug in their own API keys (BYOK) to execute these chains. A server-side run queue handles the execution, ensuring that long-running tasks—like video generation—continue even if the browser is refreshed or closed.

Who it’s for

It is designed for creators and AI enthusiasts who want to build complex, multi-modal AI workflows (such as text-to-image-to-video) without writing code or manually moving files between different AI services.

Highlights

  • Multi-Provider Integration: Native support for 11 providers including OpenAI, Anthropic, Gemini, DeepSeek, and others.
  • Infinite Canvas: A visual workspace with undo/redo, auto-layout, and typed connection rules to prevent invalid wiring.
  • Automated Reference Injection: Connected assets are automatically detected and can be mentioned in prompts using @ symbols.
  • Flexible Deployment: Available as a desktop app (macOS/Windows), a Docker container for server hosting, or a local web development setup.

Related

  • Project
    ashuoAI/SHUO-Canvas

    A node-based visual canvas for multi-modal AI creation that integrates text, image, video, and audio workflows, including support for ComfyUI and RunningHub.

  • Project
    SamurAIGPT/Vibe-Workflow

    Vibe Workflow is an open‑source, MIT‑licensed node‑based visual editor for building generative image and video pipelines. It consists of a Next.js front‑end, a FastAPI back‑end that calls MuAPI’s generative models, and a reusable workflow‑builder UI library. You can self‑host it (Docker or manual) or use the hosted SaaS version, and you can extend it with custom nodes to call any AI model or external API.

  • Project
    TeamWiseFlow/xiaobei

    Xiaobei is an open‑source AI agent (built on openclaw) that automates content creation, video production, multi‑platform publishing, analytics, and 24/7 customer support for small‑to‑medium businesses—all controlled via a WeChat chat interface.

  • Dispatch
    Workflow1111 Rebuilds AUTOMATIC1111 Features with Gradio Workflow

    Hugging Face released Workflow1111, a Gradio Workflow that replicates most of AUTOMATIC1111's stable‑diffusion‑webui functionality using 73 nodes across eleven media pipelines, enabling browser‑based multi‑model generation without a local GPU.

  • Project
    chatfire-AI/huobao-drama

    An AI-powered short-drama production platform that automates the entire pipeline from script generation and character design to storyboard breakdown and final video export.