# BytePlus

## Description **What it does**: The BytePlus component integrates a powerful suite of AI models from ByteDance, capable of handling various tasks ranging from advanced text generation to high-quality image and video synthesis. It provides users with access to Large Language Models (LLMs) for complex reasoning, as well as specialized generative models for visual media. The BytePlus component allows you to seamlessly switch between different model types (Text, Image, Video) within your workflow. You can customize parameters such as resolution, aspect ratio, and duration depending on the selected model. The BytePlus component has the identifier of byteplus-X, where X represents the instance number of the component. ## Inputs The BytePlus component has the following input connections: | Input Name | Description | Constraints | | ------------------------------ | ----------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | | **From Data Source / Trigger** | This input connection represents the context information or file inputs (images) for the model. | It can originate from a Trigger (e.g., uploaded files), Data Loader, or previous node outputs. | | **From Input** | This input connection represents the user query or prompt | It typically originates from a Text Input component or a string output from another node. | ## Component settings | Parameter Name | Description | | --------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Model |

This parameter specifies the specific BytePlus model version that the component should use.

The available options cover text, image, and video generation.

List:

DeepSeek V3.2: A high-performance Large Language Model (LLM) for text generation and reasoning.
Seed 1.6: A versatile generative model.
Seedream 4.5: Specialized for high-quality Image Generation.
Seedance 1.0 Pro / 1.5 Pro: Specialized for Video Generation.

| | Prompt |

Describes how you want the model to respond or what content you want to generate.

You can use the "Use AI" feature to help refine your prompt.

| | Image source (Applicable for Image/Video models) |

Select a source image to perform Image-to-Image or Image-to-Video generation.

Supports formats like .jpg and .png.

| | Resolution / Size *(Applicable for Seedance & Seedream models)* |

Defines the quality or pixel dimensions of the output.

Video (Seedance): e.g., 720p.
Image (Seedream): e.g., 4k.

| | Aspect ratio |

Defines the dimensions of the generated visual content.

Apply for Video (Seedance)

16:9
4:3
1:1
3:4
9:16
21:9

Apply for Image (Seedream)

1:1
2:3
3:2
3:4
4:3
4:5
5:4
9:16
16:9
21:9

| | Duration (Applicable for Seedance video models) |

Specifies the length of the generated video

List

5s (Default)
12s

| | Number of images *(Applicable for Seedream image models)* |

Specifies how many variations of the image to generate in a single run

Available values:

1 (Default)
2
3
4

| |

Switches / Toggles

Audio: Enable audio generation for video.

Enhancement: Enable AI enhancement for better visual clarity.

Compression: Optimize the output file size.

Watermark: Toggle watermarking on the output.

| ## Outputs The BytePlus component has the following output connections: This output connection contains the result of the BytePlus component. * **For DeepSeek**: Returns a text string. * **For Seedream**: Returns an Image URL. * **For Seedance**: Returns a Video URL. ## Use case **Input:** * Model = BytePlus - Seedream 4.5 * Prompt = "A cute 3D render of a robot holding a flower, pastel colors, white background" * Aspect ratio = 1:1 * Size = 4k * Number of images = 1 * Watermark = On

**Output:** Once the node executes successfully, it will return an Image URL (or a list of URLs if multiple images were requested). You can map this output to subsequent nodes

--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.diaflow.io/workflow-builder/nodes/private-ai-llm-models/byteplus.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.