ComfyUI > Nodes > Comfyui-GeminiWeb

ComfyUI Extension: Comfyui-GeminiWeb

Repo Name

Comfyui-GeminiWeb

Author
Koko-boya (Account age: 2360 days)
Nodes
View all nodes(1)
Latest Updated
2026-01-03
Github Stars
0.04K

How to Install Comfyui-GeminiWeb

Install this extension via the ComfyUI Manager by searching for Comfyui-GeminiWeb
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter Comfyui-GeminiWeb in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Comfyui-GeminiWeb Description

Comfyui-GeminiWeb is a ComfyUI node for the Gemini Web API, enabling text-to-image, image-to-image, and chat functionalities with support for multi-image inputs.

Comfyui-GeminiWeb Introduction

Comfyui-GeminiWeb is an extension designed to enhance your creative workflow by integrating Google Gemini's powerful image generation and editing capabilities directly into ComfyUI. This extension allows you to generate images from text descriptions, edit existing images using natural language, and even engage in interactive conversations about images with Gemini. By leveraging the Gemini web interface, Comfyui-GeminiWeb provides a seamless and intuitive experience for AI artists looking to explore new creative possibilities.

How Comfyui-GeminiWeb Works

At its core, Comfyui-GeminiWeb functions by connecting to the Google Gemini platform through your web browser. It uses your browser's cookies to authenticate and communicate with Gemini, allowing you to access its image generation and editing features. Think of it as a bridge that lets you use Gemini's advanced AI capabilities within the familiar environment of ComfyUI. This integration means you can easily switch between creating new images from text prompts, transforming existing images, and having insightful discussions about visual content—all without leaving ComfyUI.

Comfyui-GeminiWeb Features

  • Text-to-Image: Transform your text descriptions into stunning images using Gemini's native image model. This feature is perfect for artists who want to visualize their ideas quickly and effortlessly.
  • Image-to-Image: Modify and enhance your images by providing text-based instructions. Whether you want to change the style, add elements, or adjust the composition, this feature gives you the flexibility to refine your artwork.
  • Vision Chat: Engage in a dialogue with Gemini about your images. This feature allows you to ask questions, get feedback, and explore creative ideas interactively.
  • Multi-Image Input: Use up to five reference images to guide the image generation or editing process. This is particularly useful for maintaining consistency across a series of artworks or when working on complex compositions.
  • Watermark Filter: Choose whether to include watermarked images, non-watermarked images, or both in your results. This gives you control over the final presentation of your work.
  • Auto Authentication: Automatically detect and use your browser cookies for seamless authentication with Gemini, simplifying the setup process.
  • Self-Contained: All necessary dependencies are bundled with the extension, so you don't need to worry about installing additional API packages.

Comfyui-GeminiWeb Models

Comfyui-GeminiWeb offers several models to cater to different needs:

  • Unspecified: The default model, suitable for general use.
  • Gemini-3.0-Pro: The latest Pro model, offering advanced features and improved performance.
  • Gemini-2.5-Pro: A previous Pro model, still powerful and reliable.
  • Gemini-2.5-Flash: A faster model, ideal for quick iterations and testing. Choosing the right model can impact the quality and speed of your image generation, so consider your project's requirements when selecting a model.

Troubleshooting Comfyui-GeminiWeb

Here are some common issues you might encounter and how to resolve them:

  • "Cookie expired": If you receive this message, re-login to gemini.google.com and update your cookies in the extension.
  • "No images generated": Ensure your prompt includes the word "generate" to trigger image creation.
  • Import errors: Run pip install -r requirements.txt to ensure all dependencies are installed.
  • Region restrictions: Image generation may not be available in all regions. Check if your location supports this feature.
  • "Event loop closed": Restart ComfyUI to resolve this issue.
  • Filter not working: Each generation returns two images (watermarked and clean). Adjust your filter settings accordingly.

Learn More about Comfyui-GeminiWeb

To further enhance your experience with Comfyui-GeminiWeb, consider exploring the following resources:

  • Gemini-API Documentation: Learn more about the underlying API that powers Comfyui-GeminiWeb.
  • ComfyUI Community Forums: Connect with other AI artists, share your work, and get support from the community.
  • Google Gemini: Discover more about the capabilities of Google Gemini and how it can enhance your creative projects. By utilizing these resources, you can deepen your understanding of Comfyui-GeminiWeb and unlock its full potential in your artistic endeavors.

Comfyui-GeminiWeb Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.