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

# AI Apps

> BizyAir AI Apps are ready-to-use applications built on ComfyUI workflows — no node configuration needed.

AI Apps are out-of-the-box application-layer products built on ComfyUI workflows. They wrap node-based workflows into externally callable applications — no node configuration needed; just enter prompts or images per scenario and get results. Think of them as the application-layer entry point combining "visual wrapping of workflows + out-of-the-box use + Agent-callable".

## Core Capabilities

| Capability           | Description                                                                                                           |
| -------------------- | --------------------------------------------------------------------------------------------------------------------- |
| Out-of-the-box       | Built on ComfyUI workflows — usable without configuring nodes                                                         |
| Scenario coverage    | Covers text-to-image, image-to-image, text-to-video, image-to-video, motion transfer, render generation, and more     |
| One-click publishing | Publish a workflow as an AI app after a successful run                                                                |
| Parameter export     | Select parameters to export as the app's input fields when publishing                                                 |
| Linked workflow      | An AI app is essentially the outward presentation of a workflow; its source workflow can be viewed on the detail page |
| Multiple base models | Covers over a dozen base models such as `GPT-Image, Nano Banana, Z-Image, LTX-2, Veo, Illustrious`                    |

## Use Cases

* **Quick generation**: No ComfyUI experience needed — just get image / video results directly
* **Workflow monetization**: Package a tuned workflow as an AI app for your team or community
* **Agent invocation**: Integrate an AI app as a callable node into your product or agent
* **Scenario demos**: During teaching or client demos, pick the matching app by scenario to produce outputs fast

## Publishing an AI App

A workflow can be published as an AI app after it runs successfully.

### Pre-publish Checklist

Before clicking publish, confirm that:

* The workflow's latest draft run had no errors.
* Parameters that need external control are switched to "reference input", with names and default values defined.
* Output nodes are configured (e.g., `Save Image` path, `Save Video` filename rule).

### Publish Fields

| Field             | Description                                                         |
| ----------------- | ------------------------------------------------------------------- |
| App name          | Display name of the app                                             |
| Version name      | e.g., `V1.0 / V2.0`                                                 |
| Base model        | The base model the app is built on, e.g., `Nano Banana, GPT-Image`  |
| Cover image       | A visual introduction to the app                                    |
| App description   | Helps users understand the app's function and type                  |
| Public visibility | Choose `Public / Private`                                           |
| Export parameters | Select workflow parameters to expose as input fields for the caller |

### Publish Steps

1. After the workflow runs successfully, click `Publish` in the upper-right corner.
2. Select `Publish AI App`.
3. In the popup panel, fill in the app name, version, base model, cover, description, and other info.
4. Under "Export parameters", check the fields to expose as app inputs and set their names and default values.
5. Toggle `Public visibility` to decide whether to make it public.
6. Click `Publish App`.