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

# Vision Support

> Send images to Emby’s vision-enabled models using URLs or base64-encoded image data.

# Vision Support

Emby supports **vision-enabled models** that can understand, analyze, describe, and transform images.\
You can send images using **HTTPS URLs** or **inline base64**—fully compatible with the OpenAI Messages format your tools already use.

Vision models such as **Qwen-VL**, **DeepSeek-Vision**, **GLM-VL**, and others are available directly through:

```bash theme={null}
GET https://api.emby.dev/v1/models
```

***

## Vision-Enabled Models

Any model with `"vision": true` in the Emby model list can:

* Analyze images
* Describe objects, scenes, and text
* Perform comparisons
* Extract information (OCR-like)
* Modify or process image inputs
* Work with mixed text + image messages

***

## Sending Images to Vision Models

Images can be passed in **two formats**:

<CardGroup cols={2}>
  <Card title="HTTPS URL" icon="globe">
    Provide a publicly reachable HTTPS image URL.
  </Card>

  <Card title="Base64 Data" icon="file-image">
    Send an inline base64-encoded image directly in the request body.
  </Card>
</CardGroup>

***

## 1. Using HTTPS URLs

```bash theme={null}
curl -X POST "https://api.emby.dev/v1/chat/completions" \
  -H "Authorization: Bearer $EMBY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-vision",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "What is shown in this image?" },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/dog.jpg"
            }
          }
        ]
      }
    ]
  }'
```

***

## 2. Using Base64 Inline Data

Perfect when the image is **local**, or cannot be publicly hosted.

```bash theme={null}
curl -X POST "https://api.emby.dev/v1/chat/completions" \
  -H "Authorization: Bearer $EMBY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-vision",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Describe this image" },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,<your_base64_here>"
            }
          }
        ]
      }
    ]
  }'
```

***

## Content Format (Mixed Input)

Vision models require `content` to be an **array** when sending images.

Types:

* **Text block:**
  ```json theme={null}
  { "type": "text", "text": "Your question" }
  ```

* **Image block:**
  ```json theme={null}
  { "type": "image_url", "image_url": { "url": "<url_or_base64>" } }
  ```

***

## Sending Multiple Images

You can include **any number of images** to compare, combine, or analyze together.

```bash theme={null}
curl -X POST "https://api.emby.dev/v1/chat/completions" \
  -H "Authorization: Bearer $EMBY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-vision",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Compare these two photos." },
          {
            "type": "image_url",
            "image_url": { "url": "https://example.com/img1.jpg" }
          },
          {
            "type": "image_url",
            "image_url": { "url": "https://example.com/img2.jpg" }
          }
        ]
      }
    ]
  }'
```

***

## Simple Text-Only Messages Still Work

If no images are included, you may still send simple string content:

```bash theme={null}
curl -X POST "https://api.emby.dev/v1/chat/completions" \
  -H "Authorization: Bearer $EMBY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-vision",
    "messages": [
      { "role": "user", "content": "Hello! What models do you support?" }
    ]
  }'
```

***

## Supported Image Types

Vision models typically support:

* **JPEG** (`.jpg`, `.jpeg`)
* **PNG** (`.png`)
* **WebP** (`.webp`)
* **GIF** (`.gif`)

Most Emby-hosted models also support high-resolution input (up to 20–30MB depending on the model).

***

## Error Handling

If an image fails (wrong format, unreachable URL, base64 error), Emby handles it gracefully:

<CardGroup cols={2}>
  <Card title="Graceful Fallback" icon="triangle-exclamation">
    Emby returns a helpful error message instead of crashing your request.
  </Card>

  <Card title="Per-model Handling" icon="code">
    Some models may attempt inference with remaining images if one fails.
  </Card>
</CardGroup>

Typical error example:

```json theme={null}
{
  "error": {
    "message": "Image could not be fetched or decoded",
    "type": "invalid_image_input"
  }
}
```

***

## Need help testing vision models?

We're here to help:

**WhatsApp us:** [https://wa.absolum.nl](https://wa.absolum.nl)\
**Book a call:** [https://cal.com/absolum/30min](https://cal.com/absolum/30min)