> 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/generate_image.md).

# Generate Image

**Action ID:** `generate_image`

## Description

Use AI to generate images from your imagination. Simply describe what you want to see, and watch the AI bring it to life.

## Connection

| Name               | Description                                 | Required | Category |
| ------------------ | ------------------------------------------- | -------- | -------- |
| PixelML Connection | The PixelML connection to call PixelML API. | True     | pixelml  |

## Input Parameters

| Name             | Type     | Required | Default  | Description                                                                   |
| ---------------- | -------- | :------: | -------- | ----------------------------------------------------------------------------- |
| provider         | dropdown |     -    | Runware  | AI provider to use for image generation: Runware, Dall-e, or Stable Diffusion |
| prompt           | string   |     ✓    | -        | Detailed description of what you want to see in the generated image           |
| negative\_prompt | string   |     ✓    | -        | Description of what you don't want in the image                               |
| aspect\_ratio    | dropdown |     -    | 9:16\_HD | Aspect ratio and quality of the generated image                               |
| model\_id        | string   |     -    | null     | Specific model ID to use (Runware only)                                       |
| lora             | array    |     -    | null     | LoRA models to apply for style modification (Runware only)                    |

<details>

<summary>View JSON Schema</summary>

```json
{
  "description": "Generate image node input.",
  "properties": {
    "provider": {
      "default": "Runware",
      "enum": [
        "Runware",
        "Dall-e",
        "Stable Diffusion"
      ],
      "title": "Select provider. Default is Runware",
      "type": "string"
    },
    "prompt": {
      "description": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
      "title": "Prompt",
      "type": "string"
    },
    "negative_prompt": {
      "description": "A blurb of text describing what you do not wish to see in the output image.",
      "title": "Negative Prompt",
      "type": "string"
    },
    "aspect_ratio": {
      "default": "9:16_HD",
      "description": "The aspect ratio of the generated image.",
      "enum": [
        "1:1",
        "3:4",
        "4:3",
        "9:16",
        "16:9",
        "1:1_HD",
        "3:4_HD",
        "4:3_HD",
        "9:16_HD",
        "16:9_HD",
        "1:1_FHD",
        "3:4_FHD",
        "4:3_FHD",
        "9:16_FHD",
        "16:9_FHD"
      ],
      "title": "Aspect ratio",
      "type": "string"
    },
    "model_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The model ID to use for the image generation.",
      "title": "Model ID (Runware only)"
    },
    "lora": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The Lora model to use for the image generation.",
      "title": "Lora (Runware only)"
    }
  },
  "required": [
    "prompt",
    "negative_prompt"
  ],
  "title": "GenerateImageNodeInput",
  "type": "object"
}
```

</details>

## Output Parameters

| Name  | Type   | Description                |
| ----- | ------ | -------------------------- |
| image | string | URL of the generated image |

<details>

<summary>View JSON Schema</summary>

```json
{
  "description": "Generate image node output.",
  "properties": {
    "image": {
      "title": "Image output",
      "type": "string"
    }
  },
  "required": [
    "image"
  ],
  "title": "GenerateImageNodeOutput",
  "type": "object"
}
```

</details>

## How It Works

This node transforms text descriptions into images using advanced AI image generation models. When you provide a detailed prompt describing what you want to create, the AI model interprets your description and generates a corresponding image. The negative prompt helps refine results by specifying unwanted elements, allowing for more precise control over the output. You can choose from different providers (Runware, DALL-E, Stable Diffusion), each with unique characteristics and strengths. Advanced users can specify particular models and apply LoRA modifications for style customization when using Runware.

## Usage Examples

### Example 1: Product Photography

**Input:**

```
provider: "Runware"
prompt: "Professional product photo of a sleek wireless headphone in matte black, floating on white background, studio lighting, high resolution, commercial photography, detailed texture"
negative_prompt: "blurry, low quality, distorted, cluttered background, watermark, text"
aspect_ratio: "1:1_FHD"
```

**Output:**

```
image: "https://storage.pixelml.com/images/headphones-product-abc123.png"
```

### Example 2: Landscape Artwork

**Input:**

```
provider: "Stable Diffusion"
prompt: "Breathtaking mountain landscape at golden hour, snow-capped peaks, alpine lake reflection, dramatic clouds, vibrant sunset colors, photorealistic, 8k quality, nature photography"
negative_prompt: "people, buildings, cars, urban, artificial, cartoonish, oversaturated"
aspect_ratio: "16:9_HD"
```

**Output:**

```
image: "https://storage.pixelml.com/images/mountain-sunset-def456.png"
```

### Example 3: Character Illustration

**Input:**

```
provider: "Dall-e"
prompt: "Fantasy character portrait, elegant elven warrior with silver armor, flowing purple cape, magical aura, detailed face, digital art, concept art style, dramatic lighting"
negative_prompt: "realistic, photograph, blurry, deformed, low quality, text, watermark"
aspect_ratio: "3:4_HD"
```

**Output:**

```
image: "https://storage.pixelml.com/images/elf-warrior-ghi789.png"
```

## Common Use Cases

* **Marketing Content**: Generate custom images for social media posts, advertisements, and promotional materials
* **Product Visualization**: Create product mockups, concept designs, and marketing visuals without expensive photo shoots
* **Blog and Article Illustrations**: Produce unique featured images and article illustrations for content marketing
* **Concept Art**: Develop character designs, environment concepts, and visual references for creative projects
* **E-commerce**: Generate product lifestyle images, background scenes, and category banners
* **Presentation Graphics**: Create custom visuals, diagrams, and illustrations for business presentations
* **Social Media Content**: Produce eye-catching images for Instagram, Facebook, LinkedIn, and other platforms

## Error Handling

| Error Type               | Cause                                            | Solution                                                          |
| ------------------------ | ------------------------------------------------ | ----------------------------------------------------------------- |
| Empty Prompt             | Prompt parameter is missing or empty             | Provide a detailed description of what you want to generate       |
| Invalid Provider         | Selected provider is not available or misspelled | Choose from valid providers: Runware, Dall-e, or Stable Diffusion |
| Content Policy Violation | Prompt contains prohibited content or keywords   | Review and revise prompt to comply with content policies          |
| Generation Timeout       | Image generation taking longer than expected     | Simplify the prompt or try again after a few minutes              |
| Invalid Aspect Ratio     | Aspect ratio not supported by selected provider  | Choose a supported aspect ratio from the available options        |
| Model ID Error           | Specified model\_id doesn't exist (Runware)      | Verify the model ID is correct or leave blank for default         |
| API Connection Failed    | Cannot connect to PixelML API                    | Check your PixelML connection credentials and network status      |

## Notes

* **Provider Selection**: Runware offers fast generation with model flexibility, DALL-E excels at following complex prompts, Stable Diffusion provides artistic control
* **Prompt Engineering**: Be specific about style, lighting, colors, composition, and details. More descriptive prompts yield better results
* **Negative Prompts**: Use negative prompts to avoid common unwanted elements like blur, distortion, watermarks, and low quality
* **Aspect Ratios**: Choose aspect ratios based on use case (1:1 for social media, 16:9 for presentations, 3:4 for portraits)
* **Quality Settings**: HD and FHD suffixes indicate higher resolution. FHD takes longer but produces superior quality for professional use
* **LoRA Models**: Advanced Runware feature that applies specific artistic styles or modifications to the base model
* **Iteration**: Image generation is often iterative. Try different prompts, negative prompts, and settings to achieve desired results
* **Cost Consideration**: Higher resolution (FHD) images consume more credits. Balance quality needs with budget constraints