shrimbly/node-banana

Free and open node based generative workflows.

What it solves

Node Banana simplifies the creation of complex AI media generation pipelines. Instead of writing code or managing separate tools for different AI models, users can visually map out a sequence of operations—such as generating an image, editing it, and then turning it into a video—on a single canvas.

How it works

It uses a node-based visual editor where users drag and drop functional blocks (nodes) onto an infinite canvas and connect them via typed handles. These nodes act as triggers for various AI APIs (like Google Gemini, OpenAI, or Replicate). The system executes these nodes in dependency order, allowing data to flow from one AI model to another. It also supports importing ComfyUI workflows and can generate entire workflow structures from natural language descriptions.

Who it’s for

It is designed for creators and developers who want to build multi-step AI generation workflows for images, video, audio, and 3D models without needing to write custom integration code for every provider.

Highlights

  • Multi-Modal Generation: Supports image, video, audio, and 3D model generation in a single pipeline.
  • Dynamic Prompting: Allows the use of variables and LLM-powered text construction to create prompts that adapt per run.
  • Broad Provider Support: Integrates with Google Gemini, OpenAI, Anthropic, Replicate, fal.ai, and others.
  • ComfyUI Integration: Ability to drop ComfyUI workflows directly onto the canvas or connect to local/remote ComfyUI instances.
  • Visual Tooling: Includes a full-screen image annotation editor and a GLB viewer for 3D models.

Related

  • Project
    SamurAIGPT/Vibe-Workflow

    An open-source, node-based AI workflow builder for designing and automating generative image and video pipelines without vendor lock-in.

  • Project
    chatfire-AI/huobao-canvas

    A visual AI creation canvas that allows users to orchestrate text-to-image and video generation workflows using a node-based interface.

  • Project
    Comfy-Org/ComfyUI

    A modular, node-based AI engine for visual professionals to create complex workflows for generating images, video, audio, and 3D models with precise parameter control.

  • Project
    tigerowo/infinite-canvas

    An open-source creative workbench that integrates an infinite canvas with AI image, video, and audio generation tools for iterative visual design.

  • Project
    pixaroma/ComfyUI-Pixaroma

    ComfyUI‑Pixaroma is a genuine open‑source extension for the ComfyUI diffusion‑workflow editor. It adds a large collection of ready‑made nodes—image loading/resizing, visual crop & paint tools, 3‑D scene builder, audio‑reactive video, LoRA stacking, text utilities, XY‑plot comparison, and workflow helpers—plus built‑in help panels and example workflows. The goal is to make everyday AI‑image generation tasks more visual and user‑friendly, letting artists and developers build, preview, and tweak pipelines without leaving ComfyUI.