V2Fun API 文档

简体中文

English

简体中文

English

Appearance

文本生成图片 ​

传入一段描述，返回一张图。支持多种生成模型，可根据场景灵活选择——快速出稿、内容配图、游戏美术都适用。

典型应用场景 ​

  • 快速出稿：用文字描述换概念图，省掉来回沟通
  • 内容配图：文章封面、社媒素材批量生成
  • 游戏美术：角色设定、场景氛围图快速迭代

最佳实践 ​

TIP

  • 结构化 Prompt 出图更稳：[主体] + [动作/姿势] + [环境] + [光影] + [风格]
  • 有复杂描述时，先调 Prompt 增强接口再生图，效果更可控
  • 人脸或复杂纹理类内容建议多试几个模型，不同模型审美倾向差异明显

本页使用的 API 参考 POST /images/generations

基础示例 ​

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());

核心用例 ​

按需选模型 ​

各模型特性不同，按场景选择：

Qwen 系列
qwen-image（默认）— 速度快，中英文文字排版能力突出，指令跟随准确。

Gemini 系列
nano-banana-2-lite — 出图速度最快，成本最低，仅支持 1K 分辨率。
nano-banana-2 — 语义理解最强，可引用多张参考图，综合表现均衡。
nano-banana-pro — 画质最佳，擅长光影和材质细节，适合高要求的商业场景。
GPT 系列
gpt-image-2 — 真实感强，文字渲染精准，适合品牌和产品类图片。
gpt-image-2.5-flare — 速度优先的轻量模型，适合高频、日常的图像生成与编辑；在保持接近 GPT Image 2 画质的同时降低等待时间。
gpt-image-2.5-sunburst — 质量优先的高能力模型，适合高要求图像生成和精细编辑，在指令遵循、主体保持和细节表现方面更强。

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

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());

调整画面比例 ​

比例直接决定构图。横图（1280x720）适合风景和场景类内容，竖图（720x1280）适合人物主体或手机壁纸，方图（1024x1024）适合头像、商品图等需要居中展示的内容。

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

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());