Images

Image generation using PraisonAI capabilities

Overview

Generate images from text prompts using DALL-E and other image generation models.

Python Usage

Basic Image Generation

from praisonai.capabilities import image_generate

result = image_generate(
    prompt="A sunset over mountains",
    model="dall-e-3",
    size="1024x1024"
)

print(f"URL: {result[0].url}")
print(f"Revised prompt: {result[0].revised_prompt}")

DALL-E 2 (Faster, Lower Cost)

from praisonai.capabilities import image_generate

result = image_generate(
    prompt="A blue circle on white background",
    model="dall-e-2",
    size="256x256",
    n=1
)

print(f"URL: {result[0].url}")

Save Image to File

from praisonai.capabilities import image_generate

result = image_generate(
    prompt="A beautiful landscape",
    model="dall-e-3"
)

# Save to file
result[0].save("landscape.png")

Async Usage

import asyncio
from praisonai.capabilities import aimage_generate

async def main():
    result = await aimage_generate(
        prompt="A futuristic city",
        model="dall-e-3"
    )
    print(f"URL: {result[0].url}")

asyncio.run(main())

GPT-Image Models

from praisonai.capabilities import image_generate

# Works out of the box — response_format is auto-dropped for gpt-image-*.
result = image_generate(
    prompt="A green pixel art landscape",
    model="gpt-image-1",
)

print(result[0].b64_json[:40], "…")

Opt Out of Auto-Dropping

from praisonai.capabilities import image_generate

# Pass drop_params=False to raise if any kwarg is unsupported by the model.
result = image_generate(
    prompt="A sunset over mountains",
    model="dall-e-3",
    drop_params=False,
)

print(result[0].url)

Parameters

Parameter	Type	Default	Description
prompt	str	Required	Image description
model	str	”dall-e-3”	Model to use
n	int	1	Number of images
size	str	”1024x1024”	Image size
quality	str	”standard"	"standard” or “hd” (DALL-E 3 only)
style	str	None	”vivid” or “natural” (DALL-E 3 only)
response_format	str	”url"	"url” or “b64_json”. Honoured only for dall-e-2 and non-OpenAI providers. Silently dropped for dall-e-3 and gpt-image-* because those APIs reject it.
drop_params	bool	True	When True, LiteLLM strips any params the target model does not support. Set to False to raise on unsupported params instead.
timeout	float	600.0	Request timeout

Model-specific parameter handling

The capability wrapper drops parameters a model rejects before calling LiteLLM, so calls succeed without special-casing.

Model family	response_format	Notes
dall-e-3	Dropped by wrapper (OpenAI rejects it)	Always returns URL
gpt-image-* (e.g. gpt-image-1)	Dropped by wrapper (OpenAI rejects it)	Always returns base64
dall-e-2	Honoured	"url" or "b64_json"
Non-OpenAI providers (e.g. stability/...)	Honoured where supported	drop_params=True strips anything unsupported

drop_params=True is injected per call — the global litellm.drop_params is left untouched. The same handling applies to aimage_generate, image_edit, and aimage_edit.

Result Object

The ImageResult object contains:

• url: Image URL
• b64_json: Base64 encoded image (if requested)
• revised_prompt: DALL-E 3’s revised prompt
• model: Model used
• save(path): Method to save image to file