> For the complete documentation index, see [llms.txt](https://docs.diaflow.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.diaflow.io/workflow-builder/nodes/private-ai-llm-models/byteplus.md).

# BytePlus

### 1. The "Ready-to-Use" AI (Overview)

Zero setup, zero API keys. Just drag, drop, and start prompting using Diaflow's built-in AI credits.

BytePlus shines when you want one AI family for text, images, and video. You can write with **DeepSeek V3.2**, work with visual inputs using **Seed 1.6**, generate polished images with **Seedream**, and create short videos with **Seedance**.

### 2. How to Add the Node

On your canvas, open the node picker, search for **BytePlus**, and click it to add the node to your workflow.

<figure><img src="/files/J5EW1LmAZAvDdAVhcKSu" alt=""><figcaption></figcaption></figure>

### 3. What can you automate? (The "Wow" Use Cases)

#### 1. **The Campaign Content Factory**

Use **DeepSeek V3.2** to turn briefs, notes, and upstream workflow data into sales copy, landing page drafts, outreach messaging, or internal summaries at scale.

#### 2. **The Visual Ad Studio**

Use **Seedream** to create ad concepts, hero visuals, social creatives, and product campaign artwork without waiting on a full design cycle.

#### 3. **The Short-Form Video Builder**

Use **Seedance** to turn written ideas or visual references into short promo clips, launch teasers, and fast creative concepts for paid or organic campaigns.

### 4. Step-by-Step: Configuration & Smart Data Injection

#### 1. **Choose your Brain (Model):**

Select your model from the dropdown based on the job.

BytePlus does not use many **mini** or **flash** labels in this Platform node. As a simple rule, use the lighter text options for faster everyday work, and choose **Pro** models when output quality matters most.

Use **DeepSeek V3.2** for everyday text work. Use **Seed 1.6** when you want the model to work with images or video. Use **Seedream** for image creation and **Seedance Pro** models for higher-quality video output.

#### 2. **Write the Prompt & Inject Data:**

The easiest way to add live workflow data is to type `@` on your keyboard. Diaflow opens a visual dropdown so you can pick dynamic data from earlier steps.

Typing `{{` also works perfectly if you prefer the classic bracket syntax.

Put your task, goals, tone, and output rules directly into the main Prompt box.

If you want the node to remember earlier turns, turn on **Memory**. If you expect repeated requests, turn on **Caching** for text runs.

#### 3. **Attach Media:**

If you use **Seed 1.6**, you can pass images and short video files from earlier steps so the model can work from visual context.

If you use **Seedream**, you can also pass reference images to guide the generated result. This is useful for visual consistency across campaigns.

<figure><img src="/files/8S3X4oGoa0Ww06YsmK0o" alt=""><figcaption></figcaption></figure>

### 5. The Output: Seeing Your Results

This node returns the result based on the model you chose.

For text models, it returns generated text. For image and video models, it returns the generated media result so you can pass it into the next step.

Use `{{node_name.data}}` in your next step, like Gmail or Google Sheets, to pass the generated text or media forward.

You will also see `input_token` and `output_token`. Since Diaflow handles the billing, these tokens simply act as a meter so you can track how many credits your workflow is consuming.

For image and video runs, those token fields may show `0`. That is expected on this node.

<figure><img src="/files/WzMd2AI8OPeMXs5x4Gmi" alt=""><figcaption></figcaption></figure>

### 6. Golden Rules & Guardrails (CRITICAL PRO-TIPS)

#### **File/Image Limits:**

For **Seed 1.6**, supported image types include `jpg`, `jpeg`, `png`, `gif`, `webp`, `bmp`, `tiff`, and `tif`.

Supported video types are `mp4`, `avi`, and `mov`.

Video files must stay under **50 MB**.

Audio inside a video is not understood, so rely on the visuals only.

For **Seedream**, you can pass up to **4 reference images**.

You can generate **1 to 10 images** in a single image run.

#### **The System Prompt Trap:**

System instructions are available for BytePlus text models.

For the clearest and most consistent results, put your Persona/System instructions directly into the main Prompt box.

#### **Auto-Streaming:**

The AI will think quietly and return the full complete answer at once.

#### **Video runs can take longer:**

Video creation is not instant.

Some runs may take several minutes before the final result is ready. Give the step time to finish before retrying.

#### **Know what this node does not do:**

This node does not support live tool use inside the model response.

If you need generated images or video, that works well here. If you need the model to take action inside another app by itself, use a later workflow step for that.

### 7. Need Help?

* [**Understanding Diaflow Variables (`@` vs `{{ }}`)**](/agent-builder/agent-builder/cross-features-control/mention-tool.md)
* [**Contact Diaflow Support**](mailto:support@diaflow.io)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.diaflow.io/workflow-builder/nodes/private-ai-llm-models/byteplus.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
