Image Generation

Image Generation

Endpoint: /images/api/v1/generations

Description: Generates images based on text prompts using the configured image generation engine (OpenAI DALL-E, ComfyUI, or Automatic1111).

Authentication: Required (JWT token or Api Key)

HTTP Method: POST

Request Format:

{
	"model": "flux1-dev.safetensors",
	"prompt": "A futuristic city with flying cars and neon lights",
	"size": "1024x1024",
	"n": 1,
	"negative_prompt": "blurry, low quality"
}

Key Request Parameters:

Parameter	Type	Required	Description
model	string	No	Model to use (if different from default)
prompt	string	Yes	Text description of the desired image
size	string	No	Size of generated image (e.g., "512x512")
n	integer	No	Number of images to generate (default: 1)
negative_prompt	string	No	Characteristics to avoid in the image

Response Format:

[
	{
		"url": "/cache/image/generations/8a7b5c3d-1234-5678-abcd-ef1234567890.png"
	}
]

Key Response Fields:

Field	Type	Description
url	string	Path to access the generated image

Response Codes:

• 200: Successfully generated image(s)

• 400: Error in image generation or invalid parameters

Note: Image generation consumes user credits based on image size and quantity.