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

# ByteDanceSeedNode - ComfyUI Built-in Node Documentation

> Complete documentation for the ByteDanceSeedNode node in ComfyUI. Learn its inputs, outputs, parameters and usage.

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedNode/en.md)

## Overview

Generate text responses using ByteDance's Seed 2.0 models. Provide a text prompt and optionally include images or videos for multimodal context.

## Inputs

| Parameter       | Data Type | Required | Range                                                          | Description                                                                                                  |
| --------------- | --------- | -------- | -------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| `prompt`        | STRING    | Yes      | N/A                                                            | Text input to the model.                                                                                     |
| `model`         | COMBO     | Yes      | `"Seed 2.0 Pro"`<br />`"Seed 2.0 Lite"`<br />`"Seed 2.0 Mini"` | The Seed model used to generate the response.                                                                |
| `seed`          | INT       | Yes      | 0 to 2147483647                                                | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) |
| `system_prompt` | STRING    | No       | N/A                                                            | Foundational instructions that dictate the model's behavior. (default: "")                                   |

**Note on `model` parameter:** The `model` parameter is a dynamic combo that also accepts images and videos. You can connect image and video inputs to this parameter to provide multimodal context. A maximum of 20 images and 4 videos are supported per request.

## Outputs

| Output Name | Data Type | Description                                      |
| ----------- | --------- | ------------------------------------------------ |
| `output`    | STRING    | The generated text response from the Seed model. |

***

**Source fingerprint (SHA-256):** `d1ef73cf72e88216d40c0cf727f90c40cf783cecabe3be0e7530fe72dba6c172`