> 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/openai_generate_image.md).
# Generate Image
**Action ID:** `openai_generate_image`
## Description
Generate an image using text-to-image models. This node supports both DALL-E 3 and DALL-E 2 models with customizable resolutions and quality settings. DALL-E 3 offers superior image quality while DALL-E 2 provides faster generations with more resolution options.
## Provider
**OpenAI**
## Connection
| Name | Description | Required | Category |
| ----------------- | -------------------------------------------------- | :------: | -------- |
| OpenAI Connection | The OpenAI connection to use for image generation. | ✓ | openai |
## Input Parameters
| Name | Type | Required | Default | Description |
| ---------- | -------- | :------: | --------- | ------------------------------------------------------------------------------------ |
| model | dropdown | - | dall-e-3 | The model which will generate the image. Options: dall-e-3, dall-e-2 |
| prompt | string | ✓ | - | The text prompt to generate an image from. |
| resolution | dropdown | - | 1024x1024 | The resolution to generate the image in. Available options depend on selected model. |
| quality | dropdown | - | standard | Standard is faster, HD has better details. |
View JSON Schema
```json
{
"description": "Generate Image node input.",
"properties": {
"model": {
"default": "dall-e-3",
"description": "The model which will generate the image.",
"title": "Model",
"type": "string"
},
"prompt": {
"description": "The text prompt to generate an image from.",
"title": "Prompt",
"type": "string"
},
"resolution": {
"default": "1024x1024",
"description": "The resolution to generate the image in.",
"enum": [
"1024x1024",
"1024x1792",
"1792x1024"
],
"title": "Resolution",
"type": "string"
},
"quality": {
"default": "standard",
"description": "Standard is faster, HD has better details.",
"enum": [
"standard",
"hd"
],
"title": "Quality",
"type": "string"
}
},
"required": [
"prompt"
],
"title": "GenerateImageInput",
"type": "object"
}
```
## Output Parameters
| Name | Type | Description |
| ------- | ------- | -------------------------------------------------------------- |
| created | integer | Unix timestamp when the image was created. |
| data | array | Array of generated image objects containing URLs and metadata. |
View JSON Schema
```json
{
"description": "Generate Image node output.",
"properties": {
"created": {
"title": "Created",
"type": "integer"
},
"data": {
"items": {},
"title": "Data",
"type": "array"
}
},
"title": "GenerateImageOutput",
"type": "object"
}
```
## How It Works
This node sends your text prompt to OpenAI's image generation API along with your specified model, resolution, and quality settings. The model interprets your prompt and generates a new image from scratch. DALL-E 3 produces higher-quality, more detailed images but supports a more limited set of resolutions (1024x1024, 1024x1792, 1792x1024). DALL-E 2 is faster and offers more resolution options (1024x1024, 512x512, 256x256) but with generally lower quality. The response includes the generated image URL and metadata.
## Usage Examples
### Example 1: High-Quality Portrait
**Input:**
```
model: "dall-e-3"
prompt: "A serene portrait of a woman with flowing auburn hair in a sunlit garden, soft lighting, photorealistic style"
resolution: "1024x1024"
quality: "hd"
```
**Output:**
```
created: 1699564800
data: [
{
"url": "https://oaidalleapiprodscus.blob.core.windows.net/...",
"revised_prompt": "A serene portrait of a woman with flowing auburn hair..."
}
]
```
### Example 2: Vertical Mobile Image
**Input:**
```
model: "dall-e-3"
prompt: "A vibrant sunset over mountains, abstract watercolor style"
resolution: "1024x1792"
quality: "standard"
```
**Output:**
```
created: 1699564900
data: [
{
"url": "https://oaidalleapiprodscus.blob.core.windows.net/...",
"revised_prompt": "A vibrant sunset over mountains..."
}
]
```
### Example 3: Quick Generation with DALL-E 2
**Input:**
```
model: "dall-e-2"
prompt: "A cute robot made of recycled materials"
resolution: "512x512"
quality: "standard"
```
**Output:**
```
created: 1699565000
data: [
{
"url": "https://oaidalleapiprodscus.blob.core.windows.net/...",
"revised_prompt": "A cute robot made of recycled materials"
}
]
```
## Common Use Cases
* **Content Creation**: Generate images for articles, social media posts, or marketing materials
* **Visual Mockups**: Create quick visual prototypes and mockups during design phase
* **Illustration Generation**: Generate custom illustrations for books, presentations, or educational content
* **Product Visualization**: Create images of products in different scenarios or contexts
* **Concept Art**: Generate concept art for games, films, or creative projects
* **Marketing Assets**: Create unique visuals for advertising campaigns
* **Batch Image Generation**: Generate multiple variations of images for testing
## Error Handling
| Error Type | Cause | Solution |
| -------------------- | ---------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Invalid Prompt | Prompt contains prohibited content or is empty | Review prompt against OpenAI usage policies and ensure it's descriptive |
| Model Not Available | Selected model doesn't exist | Verify model name (dall-e-2 or dall-e-3) |
| Invalid Resolution | Resolution not supported by selected model | Use 1024x1024, 1024x1792, 1792x1024 for DALL-E 3 or 1024x1024, 512x512, 256x256 for DALL-E 2 |
| Rate Limit Exceeded | Too many requests in a short time | Implement delays between requests or upgrade plan |
| Authentication Error | Invalid or missing API key | Verify OpenAI connection is properly configured |
| Insufficient Credits | Account has insufficient API credits | Add credits to your OpenAI account |
| Timeout Error | Request took too long to process | Try again or use a faster model variant |
## Notes
* **Model Selection**: DALL-E 3 provides superior quality but costs more and supports fewer resolutions. Choose DALL-E 2 for faster, cost-effective generations.
* **Resolution Trade-offs**: Larger resolutions (1024x1792, 1792x1024) take longer to generate and cost more.
* **Quality Settings**: HD quality produces more detailed images but increases generation time and cost.
* **Prompt Engineering**: Write descriptive, detailed prompts for better results. Include style preferences (photorealistic, watercolor, etc.).
* **Revised Prompts**: DALL-E 3 may revise your prompt for safety and clarity. Check the revised\_prompt in the response.
* **Image URLs**: Generated image URLs are temporary. Download or store them if you need long-term access.
* **Costs**: Each image generation request incurs API costs. Budget accordingly for high-volume usage.