Skip to main content
POST
/
api
/
images
/
generations
Generate Image
curl --request POST \
  --url https://api.example.com/api/images/generations \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "model": "<string>",
  "size": "<string>",
  "n": 123,
  "steps": 123,
  "negative_prompt": "<string>"
}
'
{
  "url": "<string>"
}
Generate images from text prompts using various AI image generation engines including OpenAI DALL-E, Gemini Imagen, ComfyUI, and Automatic1111.

​
Request

​
Headers

​
Authorization
string
required
Bearer token for authentication

​
Body

​
prompt
string
required
Text description of the image to generate
​
model
string
Model to use for generation. Defaults to configured model.OpenAI models:
  • dall-e-2
  • dall-e-3
  • gpt-image-1
  • gpt-image-1.5
Gemini models:
  • imagen-3.0-generate-002
​
size
string
Image dimensions in format WIDTHxHEIGHT (e.g., 512x512, 1024x1024)Can also be auto for models that support dynamic sizing.
​
n
number
default:"1"
Number of images to generate
​
steps
number
Number of inference steps (for Stable Diffusion-based engines)
​
negative_prompt
string
Negative prompt describing what to avoid in the image (for Stable Diffusion-based engines)

​
Response

Returns an array of generated image objects.
​
url
string
URL path to access the generated image file

​
Example

curl -X POST https://your-domain.com/api/images/generations \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A serene mountain landscape at sunset with a lake",
    "model": "dall-e-3",
    "size": "1024x1024",
    "n": 1
  }'
Response
[
  {
    "url": "/api/v1/files/550e8400-e29b-41d4-a716-446655440000/content"
  }
]

​
Supported Engines

Configure the image generation engine in Admin Settings > Images:

​
OpenAI DALL-E

  • Cloud-based image generation
  • Models: DALL-E 2, DALL-E 3, GPT-IMAGE series
  • Requires OpenAI API key
  • Supports various sizes depending on model

​
Gemini Imagen

  • Google’s Imagen 3.0 model
  • Two endpoint methods: predict or generateContent
  • Requires Google API key

​
ComfyUI

  • Local/self-hosted image generation
  • Highly customizable workflows
  • Supports custom models and nodes
  • Configure workflow JSON and node mappings

​
Automatic1111 (Stable Diffusion WebUI)

  • Popular Stable Diffusion interface
  • Full control over generation parameters
  • Supports negative prompts and custom steps
  • Optional API authentication

​
Advanced Parameters

For Stable Diffusion-based engines (ComfyUI, Automatic1111): 
{
  "prompt": "A futuristic city at night",
  "negative_prompt": "blurry, low quality, distorted",
  "size": "768x768",
  "steps": 50,
  "n": 2
}

​
Image Storage

Generated images are:
  1. Automatically uploaded to the files system
  2. Associated with the user who generated them
  3. Accessible via the standard file content endpoint
  4. Linked to chat messages if chat_id and message_id are provided in metadata

​
Permissions

Requires the features.image_generation permission. Admin users have access by default.

​
Error Responses

​
400
Invalid parameters or generation failed
​
403
Image generation is disabled or user lacks permission
  • POST /api/images/edit - Edit existing images with prompts
  • GET /api/images/models - List available models for current engine
  • GET /api/images/config - Get image generation configuration (admin only)