> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Gemini 3.1 Flash Image
> 通过 Gemini API 调用 Google Gemini 3.1 Flash Image 进行 AI 图片生成与编辑。
Gemini 3.1 Flash Image 是 Google 的图片生成模型，通过 Anyfast 以原生 Gemini API 提供服务。支持文字生成图片，也可传入参考图片进行图片编辑。
Google 已于 2026 年 5 月 28 日将 `gemini-3.1-flash-image` 发布为 Nano Banana 2 的正式版（GA）。请使用这个稳定模型 ID 替代 `gemini-3.1-flash-image-preview`，后者已弃用并计划于 2026 年 6 月 25 日关停。
## 核心能力
* **文生图** — 根据文本描述生成图片
* **图片编辑** — 在 `inline_data` 中传入参考图，配合文字指令进行编辑
* **宽高比控制** — `1:1`、`4:3`、`3:4`、`16:9`、`9:16`
* **分辨率控制** — `512`（512px）、`1K`（\~1024px）、`2K`（\~2048px）、`4K`（\~4096px，按长边）
* **多模态输出** — 通过 `responseModalities: ["TEXT", "IMAGE"]` 同时返回图片和文字说明
> **注意：** 如果需要生成的图片返回 URL，请在创建 API 令牌时选择 **Aggregate-NanoUrl** 分组。
## 文生图示例
```bash cURL theme={null}
curl "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-image:generateContent?key=YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"role": "user",
"parts": [
{ "text": "生成一张山间日落的图片" }
]
}
],
"generationConfig": {
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {
"aspectRatio": "16:9",
"imageSize": "1K"
}
}
}'
```
```python Python theme={null}
import requests, base64
url = "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-image:generateContent"
response = requests.post(url, params={"key": "YOUR_API_KEY"}, json={
"contents": [
{
"role": "user",
"parts": [{"text": "生成一张山间日落的图片"}]
}
],
"generationConfig": {
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {"aspectRatio": "16:9", "imageSize": "1K"}
}
})
for part in response.json()["candidates"][0]["content"]["parts"]:
if "inline_data" in part:
with open("output.jpg", "wb") as f:
f.write(base64.b64decode(part["inline_data"]["data"]))
print("图片已保存至 output.jpg")
elif "text" in part:
print("说明文字：", part["text"])
```
```python GenAI SDK theme={null}
import google.genai as genai
client = genai.Client(api_key="YOUR_API_KEY")
response = client.models.generate_content(
model="gemini-3.1-flash-image",
contents="生成一张山间日落的图片",
config={
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {
"aspectRatio": "16:9",
"imageSize": "1K"
}
}
)
for candidate in response.candidates:
for part in candidate.content.parts:
if part.inline_data:
with open("output.jpg", "wb") as f:
f.write(part.inline_data.data)
print("图片已保存至 output.jpg")
elif part.text:
print("说明文字：", part.text)
```
## 图片编辑示例（传入参考图）
在同一个 `parts` 数组中同时传入 `text` 指令和 `inline_data` 参考图。
```bash cURL theme={null}
# 先将图片转为 base64：
# BASE64=$(base64 -i your_photo.jpg)
#
# 然后发送请求：
curl "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-image:generateContent?key=YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "这是我的一张照片，请在我旁边加一只羊驼"
},
{
"inline_data": {
"mime_type": "image/jpeg",
"data": ""
}
}
]
}
],
"generationConfig": {
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {
"aspectRatio": "1:1",
"imageSize": "1K"
}
}
}'
```
```python Python theme={null}
import requests, base64
# 读取并编码参考图片
with open("your_photo.jpg", "rb") as f:
image_b64 = base64.b64encode(f.read()).decode("utf-8")
url = "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-image:generateContent"
response = requests.post(url, params={"key": "YOUR_API_KEY"}, json={
"contents": [
{
"role": "user",
"parts": [
{
"text": "这是我的一张照片，请在我旁边加一只羊驼"
},
{
"inline_data": {
"mime_type": "image/jpeg",
"data": image_b64 # ← 将 base64 字符串粘贴至此
}
}
]
}
],
"generationConfig": {
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {"aspectRatio": "1:1", "imageSize": "1K"}
}
})
for part in response.json()["candidates"][0]["content"]["parts"]:
if "inline_data" in part:
with open("output.jpg", "wb") as f:
f.write(base64.b64decode(part["inline_data"]["data"]))
print("图片已保存至 output.jpg")
elif "text" in part:
print("说明文字：", part["text"])
```
```python GenAI SDK theme={null}
import google.genai as genai
from google.genai import types
client = genai.Client(api_key="YOUR_API_KEY")
# 读取图片
with open("your_photo.jpg", "rb") as f:
image_bytes = f.read()
response = client.models.generate_content(
model="gemini-3.1-flash-image",
contents=[
"这是我的一张照片，请在我旁边加一只羊驼",
types.Part.from_bytes(data=image_bytes, mime_type="image/jpeg")
],
config={
"responseModalities": ["TEXT", "IMAGE"],
"imageConfig": {
"aspectRatio": "1:1",
"imageSize": "1K"
}
}
)
for candidate in response.candidates:
for part in candidate.content.parts:
if part.inline_data:
with open("output.jpg", "wb") as f:
f.write(part.inline_data.data)
print("图片已保存至 output.jpg")
elif part.text:
print("说明文字：", part.text)
```
## 参数说明
| 参数 | 类型 | 必填 | 说明 |
| ------------------------------------------ | ------ | -- | ------------------------------------------- |
| `key` | string | 是 | API 密钥（查询参数） |
| `contents[].parts[].text` | string | 是 | 文字提示或指令 |
| `contents[].parts[].inline_data.mime_type` | string | 否 | 参考图类型：`image/jpeg`、`image/png`、`image/webp` |
| `contents[].parts[].inline_data.data` | string | 否 | Base64 编码的参考图数据 |
| `generationConfig.responseModalities` | array | 是 | `["IMAGE"]` 或 `["TEXT", "IMAGE"]` |
| `generationConfig.imageConfig.aspectRatio` | string | 否 | `1:1` / `4:3` / `3:4` / `16:9` / `9:16` |
| `generationConfig.imageConfig.imageSize` | string | 否 | `512` / `1K` / `2K` / `4K`（默认 `1K`） |
查看 Gemini 3.1 Flash Image 的交互式 API Playground。