Gemini image generation

Generate images from prompts with Gemini generateContent

POST /v1beta/models/{model}:generateContent

Gemini image generation

cURL

curl --request POST \
  --url https://api.bianxie.ai/v1beta/models/{model}:generateContent

import requests

url = "https://api.bianxie.ai/v1beta/models/{model}:generateContent"

response = requests.post(url)

print(response.text)

const options = {method: 'POST'};

fetch('https://api.bianxie.ai/v1beta/models/{model}:generateContent', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.bianxie.ai/v1beta/models/{model}:generateContent",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.bianxie.ai/v1beta/models/{model}:generateContent"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.bianxie.ai/v1beta/models/{model}:generateContent")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.bianxie.ai/v1beta/models/{model}:generateContent")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

Image generation shares the Gemini generateContent endpoint. Replace {model} with an image-capable model ID from the live model page.

Field	Type	Required	Description
model	path string	Yes	Image-capable Gemini model ID.
contents	array	Yes	Input content, normally containing a text part.
contents[].parts[].text	string	Yes	Image prompt.
generationConfig.imageConfig.aspectRatio	string	No	Output ratio such as 1:1, 9:16, or 16:9.

cURL

curl "https://api.bianxie.ai/v1beta/models/your-model:generateContent" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "An orange cat in a space helmet, cinematic lighting"}]
    }],
    "generationConfig": {
      "imageConfig": {"aspectRatio": "1:1"}
    }
  }'

import base64
import requests

response = requests.post(
    "https://api.bianxie.ai/v1beta/models/your-model:generateContent",
    headers={"Authorization": "Bearer API_KEY"},
    json={
        "contents": [{"role": "user", "parts": [{"text": "An orange cat in a space helmet"}]}],
        "generationConfig": {"imageConfig": {"aspectRatio": "1:1"}},
    },
    timeout=120,
)
response.raise_for_status()
for candidate in response.json().get("candidates", []):
    for part in candidate.get("content", {}).get("parts", []):
        image = part.get("inlineData")
        if image and image.get("data"):
            open("output.png", "wb").write(base64.b64decode(image["data"]))

import { writeFile } from "node:fs/promises";
const response = await fetch("https://api.bianxie.ai/v1beta/models/your-model:generateContent", {
  method: "POST",
  headers: { Authorization: "Bearer API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({
    contents: [{ role: "user", parts: [{ text: "An orange cat in a space helmet" }] }],
    generationConfig: { imageConfig: { aspectRatio: "1:1" } }
  })
});
const data = await response.json();
const image = data.candidates?.[0]?.content?.parts?.find((part) => part.inlineData)?.inlineData;
if (image?.data) await writeFile("output.png", Buffer.from(image.data, "base64"));

Read images from candidates[].content.parts[].inlineData. mimeType identifies the format and data contains Base64. A text part containing a Markdown data URL may appear as a compatibility fallback. Use a client timeout of at least 120 seconds and inspect finish and safety feedback when no image is returned.