Text to Image

Transform text instructions into visually striking images using our self-developed large-scale diffusion models. The system understands complex semantic logic and precisely controls lighting, materials, and composition. Whether it's a realistic photographic masterpiece or imaginative illustrative art, generate it with a single click.

Typical Application Scenarios

Creative Design: Quickly generate visual sketches based on abstract concepts, shortening the validation cycle.
Content Creation: Provide high-quality original images for articles, video covers, and social media content.
Game Art: Rapidly iterate on character concept designs, environmental mood boards, or UI decorative assets.

Best Practices

TIP

Use "Structured Prompts": [Subject] + [Action] + [Environment] + [Lighting/Material] + [Art Style].
For scenarios requiring extreme precision, we recommend using the "Prompt Enhancement" API first to optimize your keywords.
When generating images with faces or complex textures, try different models to achieve the best aesthetic performance.

API Reference used on this page POST /images/generations

Basic Examples

cURLJavaScriptPythonJava

bash

curl -X POST 'https://api.v2fun.ai/api/v1/images/generations' \
  -H 'Authorization: Bearer $V2FUN_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
      "prompt": "A beautiful sunset over the mountains"
    }'

javascript

const response = await fetch('https://api.v2fun.ai/api/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer $V2FUN_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "prompt": "A beautiful sunset over the mountains"
  }),
});
const data = await response.json();

python

import requests

resp = requests.post(
    'https://api.v2fun.ai/api/v1/images/generations',
    headers={
        'Authorization': 'Bearer $V2FUN_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        "prompt": "A beautiful sunset over the mountains"
    },
)
print(resp.json())

java

import java.net.URI;
import java.net.http.*;

HttpClient client = HttpClient.newHttpClient();
String body = "{\"prompt\":\"A beautiful sunset over the mountains\"}";
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.v2fun.ai/api/v1/images/generations"))
    .header("Authorization", "Bearer $V2FUN_API_KEY")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(body))
    .build();
HttpResponse<String> response = client.send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

Core Use Cases

Model Aesthetic Selection

Each model has distinct strengths — choose by scenario:

Qwen
qwen-image (default) — fast, strong instruction following, excellent for text/layout.

Gemini
nano-banana-2-lite — fastest output, lowest cost, 1K resolution only.
nano-banana-2 — best semantic understanding, supports multi-image references.
nano-banana-pro — best image quality, excels at lighting and material detail.
GPT
gpt-image-2 — realistic rendering, precise text, great for brand and product imagery.
gpt-image-2.5-flare — a speed-optimized lightweight model for high-volume, everyday image generation and editing, offering quality comparable to GPT Image 2 with lower latency.
gpt-image-2.5-sunburst — a quality-focused model for demanding generation and precise editing, with stronger instruction following, subject preservation, and detail fidelity.

model: qwen-image · nano-banana-pro · nano-banana-2 · nano-banana-2-lite · gpt-image-2 · gpt-image-2.5-sunburst · gpt-image-2.5-flare

cURLJavaScriptPythonJava

bash

curl -X POST 'https://api.v2fun.ai/api/v1/images/generations' \
  -H 'Authorization: Bearer $V2FUN_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
      "prompt": "a cinematic shot of a lone traveler in a vast desert, golden hour lighting",
      "model": "nano-banana-pro"
    }'

javascript

const response = await fetch('https://api.v2fun.ai/api/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer $V2FUN_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "prompt": "a cinematic shot of a lone traveler in a vast desert, golden hour lighting",
    "model": "nano-banana-pro"
  }),
});
const data = await response.json();

python

import requests

resp = requests.post(
    'https://api.v2fun.ai/api/v1/images/generations',
    headers={
        'Authorization': 'Bearer $V2FUN_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        "prompt": "a cinematic shot of a lone traveler in a vast desert, golden hour lighting",
        "model": "nano-banana-pro"
    },
)
print(resp.json())

java

import java.net.URI;
import java.net.http.*;

HttpClient client = HttpClient.newHttpClient();
String body = "{\"prompt\":\"a cinematic shot of a lone traveler in a vast desert, golden hour lighting\",\"model\":\"nano-banana-pro\"}";
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.v2fun.ai/api/v1/images/generations"))
    .header("Authorization", "Bearer $V2FUN_API_KEY")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(body))
    .build();
HttpResponse<String> response = client.send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

Composition Aspect Ratio

Different aspect ratios profoundly affect the model's composition logic. For example, 1280x720 is better for grand panoramic narratives, while 720x1280 better highlights the slender lines of a main character.

size: 1024x1024 · 1152x864 · 864x1152 · 1280x720 · 720x1280

cURLJavaScriptPythonJava

bash

curl -X POST 'https://api.v2fun.ai/api/v1/images/generations' \
  -H 'Authorization: Bearer $V2FUN_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
      "prompt": "a tall cyberpunk skyscraper reaching the clouds",
      "size": "720x1280"
    }'

javascript

const response = await fetch('https://api.v2fun.ai/api/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer $V2FUN_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "prompt": "a tall cyberpunk skyscraper reaching the clouds",
    "size": "720x1280"
  }),
});
const data = await response.json();

python

import requests

resp = requests.post(
    'https://api.v2fun.ai/api/v1/images/generations',
    headers={
        'Authorization': 'Bearer $V2FUN_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        "prompt": "a tall cyberpunk skyscraper reaching the clouds",
        "size": "720x1280"
    },
)
print(resp.json())

java

import java.net.URI;
import java.net.http.*;

HttpClient client = HttpClient.newHttpClient();
String body = "{\"prompt\":\"a tall cyberpunk skyscraper reaching the clouds\",\"size\":\"720x1280\"}";
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.v2fun.ai/api/v1/images/generations"))
    .header("Authorization", "Bearer $V2FUN_API_KEY")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(body))
    .build();
HttpResponse<String> response = client.send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

Images

3D Models

Motions

Videos

Balance

Text to Image

Typical Application Scenarios

Best Practices

Basic Examples

Core Use Cases

Model Aesthetic Selection

Composition Aspect Ratio

Text to Image ​

Typical Application Scenarios ​

Best Practices ​

Basic Examples ​

Core Use Cases ​

Model Aesthetic Selection ​

Composition Aspect Ratio ​

Text to Image

Typical Application Scenarios

Best Practices

Basic Examples

Core Use Cases

Model Aesthetic Selection

Composition Aspect Ratio