Text-to-Image Generation

Feature Description

Text-to-image models can generate corresponding images based on text descriptions input by users. These models support various styles and themes, capable of producing high-quality images suitable for multiple fields such as creative design and artistic creation.

Note

Although they are all text-to-image models, different models may have inconsistent calling parameters. For specific parameters and their meanings, please refer to the experience interface of the corresponding model.

Text-to-Image Model List

MoArk provides a rich selection of text-to-image models. You can view and experience these models in the Model Square.

Loading Serverless API service list...

Calling Text-to-Image Models

Using OpenAI SDK

You can use the OpenAI SDK to call text-to-image models. Here is an example using Python:

python

from openai import OpenAI
import base64

client = OpenAI(
	base_url="https://moark.ai/v1",
	api_key="XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX", # Replace with your access token
	default_headers={"X-Failover-Enabled":"true"},
)

response = client.images.generate(
	prompt="a white siamese cat", # Replace with your text description
	model="Kolors", # Replace with your selected model name
	size="1024x1024",
	extra_body={
		"num_inference_steps": 25,
		"guidance_scale": 7.5,
	},
)

image_base64 = response.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the image to a file
with open("Kolors-output.png", "wb") as f:
	f.write(image_bytes)

Using Requests Library

If you prefer not to use the OpenAI SDK, you can directly use the requests library to call text-to-image models. Here's a Python example:

python

import requests
import base64
import json

url = "https://moark.ai/v1/images/generations"

headers = {
    "Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",  # Replace with your access token
    "Content-Type": "application/json",
    "X-Failover-Enabled": "true"
}

data = {
    "prompt": "a white siamese cat",  # Replace with your text description
    "model": "Kolors",  # Replace with your selected model name
    "size": "1024x1024",
    "response_format": "b64_json",
    "num_inference_steps": 25,
    "guidance_scale": 7.5
}

response = requests.post(url, headers=headers, json=data)

if response.status_code == 200:
    result = response.json()
    image_base64 = result["data"][0]["b64_json"]
    image_bytes = base64.b64decode(image_base64)

    # Save the image to a file
    with open("Kolors-output.png", "wb") as f:
        f.write(image_bytes)

    print("Image generated successfully and saved as Kolors-output.png")
else:
    print(f"Request failed, status code: {response.status_code}")
    print(f"Error message: {response.text}")

For other programming languages, you can refer to the sample codes in the API Documentation.