> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Workflow Canvas (Editor)

## **4.1 Overview of the Editor Interface**

The canvas is a visual editor where you build workflows by placing and connecting nodes.

***

## **4.2 Node Library**

### **GMI Official Nodes**

GMI Official nodes are fully managed API-backed nodes covering four generation modalities: **Image**, **Video**, **Audio**, and **LLM**. Additional utility nodes include **GMI Image Upload** and **Batch Images**.

Each node accepts a specific input type (text, image, video, or audio) and produces a corresponding output. Nodes are sourced from our partner ecosystem and are updated regularly as new models become available.

#### **4.2.1 Video Nodes**

Video nodes generate or transform video content. They fall into three input categories:

| **Input Type** | **What it does**                      | **Example Models**                                              |
| :------------- | :------------------------------------ | :-------------------------------------------------------------- |
| Text → Video   | Generates a video from a text prompt  | Wan, Veo, Sora, Kling, Minimax Hailuo, PixVerse, Seedance, Luma |
| Image → Video  | Animates a still image into a video   | Wan, Kling                                                      |
| Video → Video  | Edits or transforms an existing video | Wan, Kling, Bria                                                |

💡 The full list of available video models is visible in the node library panel inside the editor. New models are added regularly.

***

#### **4.2.2 Image Nodes**

Image nodes generate or edit images. They fall into three input categories:

| **Input Type**       | **What it does**                      | **Example Models**                                      |
| :------------------- | :------------------------------------ | :------------------------------------------------------ |
| Text → Image         | Generates an image from a text prompt | Google (Gemini), Seedream, Tongyi (Alibaba), Reve, Bria |
| Image → Image        | Edits or transforms an existing image | SeedEdit, Reve, Bria                                    |
| Image + Mask → Image | Fills or replaces a selected region   | Bria                                                    |

💡 The full list of available image models is visible in the node library panel inside the editor.

***

#### **4.2.3 Audio Nodes**

Audio nodes generate speech or clone voices from text and audio inputs.

**Note:** Only **WAV** and **MP3** file formats are supported for audio uploads.

| **Input Type**              | **What it does**                         | **Example Models**           |
| :-------------------------- | :--------------------------------------- | :--------------------------- |
| Text → Audio                | Converts text to natural-sounding speech | Inworld, Minimax, ElevenLabs |
| Text + Voice Sample → Audio | Clones a voice and speaks the given text | Inworld, Minimax, Step Audio |

💡 The full list of available audio models is visible in the node library panel inside the editor.

***

### **ComfyUI Nodes**

Native ComfyUI nodes sourced directly from the official ComfyUI repository. These include standard preprocessing, conditioning, and utility nodes commonly used in ComfyUI workflows.

***

### **When to Use GMI Official Nodes vs. ComfyUI Nodes**

|                   | **GMI Official Nodes**         | **ComfyUI Nodes**                  |
| :---------------- | :----------------------------- | :--------------------------------- |
| **Best for**      | Quick setup, managed inference | Fine-grained control, custom logic |
| **Control level** | Simplified inputs/outputs      | Full node-level customization      |
| **Performance**   | Optimized, fully managed       | Depends on workflow configuration  |

***

## **4.3 Canvas Basics**

* **Add Node:** Right-click → Add Node, or search in the node library panel
* **Delete Node:** Select the node and click the trash icon
* **Drag & Arrange:** Move nodes freely on the canvas
* **Connect Nodes:** Drag from the output of one node to the input of another — data types must match for the connection to be valid

***

## **4.4 Toolbar Functions**

* **Run:** Execute the workflow
* **Save:** Save workflow changes