> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/reference/nodes/pml_edit_image.md).

# Edit Image

**Action ID:** `pml_edit_image`

## Description

Edit an image using a prompt.

## Connection

| Name               | Description                                       | Required | Category |
| ------------------ | ------------------------------------------------- | -------- | -------- |
| PixelML Connection | The PixelML connection to use for the edit image. | True     | pixelml  |

## Input Parameters

| Name        | Type    | Required | Default | Description                                                    |
| ----------- | ------- | :------: | ------- | -------------------------------------------------------------- |
| prompt      | string  |     ✓    | -       | The prompt to edit the image                                   |
| images      | array   |     ✓    | -       | The images to use for the edit (JPG/PNG)                       |
| temperature | number  |     -    | 0.9     | Controls randomness (0-1). Lower values are more deterministic |
| max\_tokens | integer |     -    | 2048    | Maximum tokens to generate (2048-4096)                         |
| top\_p      | number  |     -    | 1       | Nucleus sampling parameter for token selection                 |

<details>

<summary>View JSON Schema</summary>

```json
{
  "description": "Edit Image action input.",
  "properties": {
    "prompt": {
      "description": "The prompt to edit the image.",
      "title": "Prompt",
      "type": "string"
    },
    "images": {
      "description": "The images to use for the chat.",
      "items": {
        "type": "string"
      },
      "title": "Images",
      "type": "array"
    },
    "temperature": {
      "default": 0.9,
      "description": "Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.",
      "maximum": 1,
      "minimum": 0,
      "title": "Temperature",
      "type": "number"
    },
    "max_tokens": {
      "default": 2048,
      "description": "The maximum number of tokens to generate. Requests can use up to 2,048 or 4,096 tokens shared between prompt and completion depending on the model.",
      "title": "Maximum Tokens",
      "type": "integer"
    },
    "top_p": {
      "default": 1,
      "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.",
      "title": "Top P",
      "type": "number"
    }
  },
  "required": [
    "prompt",
    "images"
  ],
  "title": "PMLEditImageActionInput",
  "type": "object"
}
```

</details>

## Output Parameters

| Name    | Type | Description                                       |
| ------- | ---- | ------------------------------------------------- |
| content | any  | The edited image or response content from PixelML |

<details>

<summary>View JSON Schema</summary>

```json
{
  "description": "Edit Image action output.",
  "properties": {
    "content": {
      "title": "Content"
    }
  },
  "required": [
    "content"
  ],
  "title": "PMLEditImageActionOutput",
  "type": "object"
}
```

</details>

## How It Works

This node uses PixelML's AI-powered image editing capabilities to modify images based on text prompts. You provide one or more source images along with a descriptive prompt explaining the desired edits. The AI model processes the prompt and images, applying transformations such as style changes, object additions/removals, color adjustments, or content modifications. The temperature and token parameters control the creativity and output length of the generation process.

## Usage Examples

### Example 1: Change Image Style

**Input:**

```
prompt: "Make this image look like a watercolor painting"
images: ["https://example.com/photo.jpg"]
temperature: 0.7
max_tokens: 2048
```

**Output:**

```
content: {
  "url": "https://pixelml.com/edited/watercolor-image.png",
  "format": "png"
}
```

### Example 2: Remove Background Objects

**Input:**

```
prompt: "Remove all people from this street scene"
images: ["https://example.com/street.jpg"]
temperature: 0.3
max_tokens: 2048
```

**Output:**

```
content: {
  "url": "https://pixelml.com/edited/empty-street.png"
}
```

### Example 3: Add Creative Elements

**Input:**

```
prompt: "Add autumn leaves falling in the background"
images: ["https://example.com/portrait.jpg"]
temperature: 0.9
max_tokens: 3000
```

**Output:**

```
content: {
  "url": "https://pixelml.com/edited/autumn-portrait.png"
}
```

## Common Use Cases

* **Product Photography**: Modify product images by changing backgrounds, colors, or adding props
* **Photo Retouching**: Remove unwanted objects, blemishes, or people from photographs
* **Creative Transformations**: Apply artistic styles like oil painting, sketch, or cartoon effects
* **Image Composition**: Add or modify elements within existing images based on text descriptions
* **Background Replacement**: Change or enhance backgrounds while preserving foreground subjects
* **Color Grading**: Adjust mood, tone, and color palette of images using natural language descriptions
* **Fashion and Design**: Visualize clothing or design changes on existing product photos

## Error Handling

| Error Type           | Cause                                             | Solution                                                                         |
| -------------------- | ------------------------------------------------- | -------------------------------------------------------------------------------- |
| Connection Failed    | Invalid or missing PixelML connection credentials | Verify your PixelML connection is properly configured with valid API credentials |
| Invalid Image URL    | Image URL is not accessible or invalid format     | Ensure image URLs are publicly accessible and in JPG or PNG format               |
| Prompt Too Vague     | Editing prompt is unclear or ambiguous            | Provide specific, descriptive prompts with clear editing instructions            |
| Token Limit Exceeded | max\_tokens set too high for the model            | Reduce max\_tokens to 2048 or check model limits                                 |
| Unsupported Format   | Image format not supported by PixelML             | Convert images to JPG or PNG format before processing                            |
| Rate Limit Exceeded  | Too many API requests in short period             | Implement delays between requests or upgrade your PixelML plan                   |
| Processing Timeout   | Complex edits taking too long to process          | Simplify the editing prompt or reduce image resolution                           |

## Notes

* **Image Formats**: Only JPG and PNG image formats are supported. Ensure your images are in one of these formats before processing.
* **Temperature Control**: Lower temperature (0.0-0.3) produces more consistent, predictable edits. Higher temperature (0.7-1.0) generates more creative and varied results.
* **Prompt Specificity**: The more specific and detailed your prompt, the better the results. Include information about style, mood, colors, and specific changes desired.
* **Image URLs**: All image URLs must be publicly accessible. The PixelML service needs to download them for processing.
* **Token Management**: Higher max\_tokens allows for more complex edits but increases processing time and cost. Start with the default 2048 for most tasks.
* **Multiple Images**: You can provide multiple images in the array, useful for batch processing or providing reference images for the editing style.
* **API Costs**: Each edit operation consumes PixelML API credits. Monitor your usage to avoid unexpected costs.