Skip to content

Image

This quickstart walks you through generating your first image with Siraya AI.

Image generation

curl https://image.siraya.pro/v1/images/generations \
    -H "Content-Type: application/json" \
    -H "Authorization: <API_KEY>" \
    -d '{
    "model": "openai/gpt-image-1-text-to-image",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "output_format": "url"
  }'


from openai import OpenAI
import base64
import os

client = OpenAI(
    api_key="<API_KEY>", # Replace with your Key "sk-***"
    base_url="https://image.siraya.pro/v1"
)

prompt = """A cute baby sea otter."""

result = client.images.generate(
    model="openai/gpt-image-1-text-to-image",
    prompt=prompt,
    n=1,
    output_format="url"
)

print(result)
  • https://image.siraya.pro/v1/images/generations is the base URL
  • <API_KEY> is your API Key generated in API page.
  • model is the model name, such as gpt-image-1, available model list can be access in Model page.
  • prompt is the prompt.
  • n is the number of images to generate, default value is 1.
  • output_format indicate the output format, default value is url.
  • b64_json
  • url

Example response

{
    "data": [
        {
            "url": "https://resource.siraya.pro/image/generated%2Fsiraya_848a9432-b9ee-4e58-9ea4-adf390ab61ac.png",
            "b64_json": "",
            "revised_prompt": ""
        }
    ],
    "created": 1760177063
}

Image editing

curl https://image.siraya.pro/v1/images/edits \
    -H "Content-Type: application/json" \
    -H "Authorization: <API_KEY>" \
    --data-raw '{
    "model": "jia-lab/dreamomni2-image-to-image",
    "prompt": "Replace the first image have the same image style as the second image.",
    "image_urls": [
        "https://resource.trustai.sg/image/generated%2Fsiraya_a146ee8a-1fe2-43ce-803a-fb1e7f3f6949.png",
        "https://resource.siraya.pro/image/generated%2Fsiraya_fe4771ae-d67c-41bb-a366-b07f1411ae06.png"
    ],
    "n": 1,
    "output_format": "url"
}'

  • https://image.siraya.pro/v1/images/edits is the base URL
  • <API_KEY> is your API Key generated in API page.
  • model is the model name, such as dreamomni2-image-to-image, available model list can be access in Model page.
  • prompt is the prompt.
  • image_urls is the list of URLs of input images for editing.
  • n is the number of images to generate, default value is 1.
  • output_format indicate the output format, default value is url.
  • b64_json
  • url

Example response

{
    "data": [
        {
            "url": "https://resource.trustai.sg/image/generated%2Fsiraya_a146ee8a-1fe2-43ce-803a-fb1e7f3f6949.png",
            "b64_json": "",
            "revised_prompt": ""
        }
    ],
    "created": 1760177063
}