Image Generation

Create stunning images from text descriptions using the OpenAI-compatible API.

Generate high-quality images using models like SDXL Lightning, Flux, and Stable Diffusion all through a standard /v1/images/generations endpoint.

Available Models

Model	API ID	Tier	Resolution
Stable Diffusion 1.5	stable-diffusion-1.5	Free	512×512
SDXL Lightning	sdxl_lightning_4step.safetensors	Pro	1024×1024
Flux.1 Schnell	flux.1-schnell	Pro	1024×1024
Oxlo Image Pro	oxlo-image-pro	Premium	1024×1024

Text-to-Image

Generate an image from a text prompt:

import openai
import base64

client = openai.OpenAI(
    base_url="https://api.oxlo.ai/v1",
    api_key="<YOUR_API_KEY>"
)

response = client.images.generate(
    model="sdxl_lightning_4step.safetensors",
    prompt="A futuristic city skyline at sunset, digital art",
    n=1,
    size="1024x1024"
)

# Decode and save the image
image_data = base64.b64decode(response.data[0].b64_json)
with open("output.png", "wb") as f:
    f.write(image_data)

print("Image saved to output.png")

OpenAI Compatible: Oxlo.ai image generation works with client.images.generate() from the official OpenAI SDK.

Response Format

Images are returned as base64-encoded JSON:

json

{
  "created": 1234567890,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhE..."
    }
  ]
}

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model ID (e.g., `sdxl_lightning_4step.safetensors`)
prompt	string	Yes	Text description of the image to generate
n	integer	No	Number of images to generate (default: 1)
size	string	No	Image size (default: `1024x1024`)

Image-to-Image (img2img)

Transform an existing image using a text prompt. This uses the /v1/images/edits endpoint. Supported models: Stable Diffusion 1.5, SDXL Lightning, and Oxlo Image Pro.

Additional Parameters for img2img

Parameter	Type	Required	Description
image	string	Yes	Base64-encoded source image (with or without `data:image/...` prefix)
prompt	string	Yes	Text describing the desired transformation
strength	float	No	How much to transform the original (0.0 = keep original, 1.0 = fully new). Default: `0.75`

img2img Example

import openai
import base64

client = openai.OpenAI(
    base_url="https://api.oxlo.ai/v1",
    api_key="<YOUR_API_KEY>"
)

# Read and encode source image
with open("source.jpg", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode("utf-8")

response = client.images.edit(
    model="stable-diffusion-1.5",
    image=f"data:image/jpeg;base64,{image_b64}",
    prompt="Transform this into a watercolor painting",
    extra_body={"strength": 0.75}
)

# Save result
result = base64.b64decode(response.data[0].b64_json)
with open("output.png", "wb") as f:
    f.write(result)

print("Transformed image saved!")