# Describe Image

> Describe any image in words with a vision model, briefly, in detail or in labeled sections, and send the text to prompts, captions or alt text.

Source: https://nodaro.ai/docs/nodes/image/describe-image

The **Describe Image** node looks at an image with a vision model and writes a text description of it. You choose how much detail you want, or write your own question, and the node returns text for prompts, captions or alt text. The output is text, not an image.

- Found in: Image › Understand
- Output: text
- API type: `image-to-text`

## When to use it
- Caption generated images for social posts or for accessibility.
- Turn an existing picture into a prompt, to make new images in the same spirit.
- Describe a reference image in labeled sections for later AI nodes.
- Write alt text automatically in a content workflow.
- Feed image descriptions into [Generate Script](https://nodaro.ai/docs/nodes/video/generate-script) to build a story around pictures.

## Quick start
### Add the node

Press Tab on the canvas and choose **Image › Understand › Describe Image**.

### Connect the image

Drag from an image node, such as [Upload Image](https://nodaro.ai/docs/nodes/image/upload-image) or [Generate Image](https://nodaro.ai/docs/nodes/image/generate-image), to the **Image** input.

### Choose the detail

Open the settings panel and choose a **Detail Level**. To ask something specific, write it in **Custom Prompt (optional)** instead.

### Run it

Click **Run** on the node. The description appears on the node, where you can copy it or download it as a text file. Wire the **Text** output into any node that takes text.

Workflow: Describe Image turns an artwork into a description, and the description becomes the prompt of a new image.

- Upload Image → Describe Image (image)
- Describe Image → Generate Image (prompt)

## Inputs
| Input | Accepts | What it does |
| --- | --- | --- |
| **Image** | Image nodes, such as Upload Image, Generate Image and Modify Image | The picture to describe. Required. |

The output, **Text**, is the description. It connects to any text input, such as the **Prompt** input of Generate Image, [Combine Text](https://nodaro.ai/docs/nodes/automate/combine-text) or Generate Script.

## Settings
| Setting | What it does |
| --- | --- |
| **Detail Level** | **Brief (1-2 sentences)**, **Detailed (3-6 sentences)** or **Structured (labeled sections)**. The default is **Detailed**, which writes flowing prose. **Structured** returns the sections Subject, Setting, Colors, Lighting, Mood and Details. |
| **AI Model** | The vision model. The default is Claude Sonnet 4.6. The model sets the quality of the description and its price tier. |
| **Reasoning Effort** | How much the model reasons before it answers, on models that support it. The default is **Auto (model default)**. |
| **Advanced mode** | Gemini models only. Runs the model on the provider directly, so that **Temperature** and **Max Tokens** take effect. Costs one credit tier more. |
| **Custom Prompt (optional)** | Your own instruction, up to 2,000 characters. When you write one, it replaces the detail level completely. |
| **Pre & post text** | Text that is always added before and after the instruction. It is hidden from people who use your workflow as an app. See [Prompt pre and post text](https://nodaro.ai/docs/concepts/prompt-pre-post-text). |

When **Custom Prompt (optional)** is empty and you set pre or post text, that text becomes the whole instruction and replaces the built-in one.

When the node has more than one result, **Result History** in the settings panel lets you switch between them.

## Start from a preset

Describe Image has factory presets for common jobs. Open the preset menu on the node and choose one:

| Folder | Presets |
| --- | --- |
| Accessibility & SEO | Alt Text, SEO Caption, Social Caption |
| Extraction | OCR, Tags, Product Description |
| Creative | Detailed Description, Reverse Prompt |

Read [Presets](https://nodaro.ai/docs/concepts/presets) to save your own.

## Credits
A run costs 3 credits with the default model, Claude Sonnet 4.6. The price follows the tier of the model: economy models cost less and premium models cost more. **Advanced mode** moves the price up one tier. The **Run** button shows the exact price before you run.

## Tips
- **Brief for prompts with context.** Use **Brief** when the description feeds a node that has its own context, such as a script generator.
- **Structured for later nodes.** Use **Structured** when later nodes need the subject, the colors or the lighting separately.
- **Detailed for captions.** Use **Detailed** for flowing captions and alt text.
- **Ask for what you need.** A custom prompt such as "Describe the fashion items in this image, with colors and materials" gives focused results.
- **Keep the default instructions if you need them.** A custom prompt replaces the built-in instruction. To extend the default behavior instead, include those instructions in your own prompt.

## Frequently asked questions

### Which model does Describe Image use?

Claude Sonnet 4.6 by default. You can choose another vision model under AI Model, and the price follows the tier of the model you choose.

### How many credits does Describe Image cost?

3 credits per run with the default model. Economy models cost less and premium models cost more, and the node shows the exact price before you run it.

### Can I ask a specific question about an image?

Yes. Write your own instruction in Custom Prompt, for example "List the fashion items and their colors". A custom prompt replaces the detail level completely.

### How do I turn an image into a prompt for a new image?

Wire the Text output of Describe Image into the Prompt input of Generate Image. The Reverse Prompt preset is made for this job.

### What does the Structured detail level return?

Labeled sections for the subject, the setting, the colors, the lighting, the mood and the details, which later nodes can read part by part.