图像生成工具让 Grok 可以在对话中使用 Grok Imagine 创建和编辑图像。该工具使用最新的 Imagine 图像模型（grok-imagine-image-2.0）。你向模型提供该工具；模型会决定何时调用它、编写图像 prompt、选择宽高比，并将最终图像与文本响应一并返回。由于该工具在服务端运行，模型还可以在单个请求中串联调用，例如先生成图像，再编辑图像。

如果已有精确的 prompt，并希望直接控制宽高比和分辨率，请改用图像生成和图像编辑 endpoint。当图像创建只是更大的对话或智能体工作流中的一个步骤时，再使用该工具。

SDK 支持

SDK/API	工具名称
xAI SDK	`image_generation`
OpenAI Responses API	`image_generation`

所有与 Responses API 兼容的 SDK 也支持该工具。Vercel AI SDK 尚未提供图像生成工具。

将 image_generation 添加到 tools 并请求生成图像。在 xAI SDK 中，每张生成的图像通过 response.image_outputs 以解码后的字节形式提供，可直接写入文件。在 Responses API 中，每张图像以 image_generation_call 输出项的形式返回，其 result 字段包含不带 data-URL 前缀的 base64 编码图像，因此可以直接解码。

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

response = client.responses.create(
    model="grok-4.7",
    input="Generate an image of a corgi surfing a big wave, in the style of a Japanese woodblock print",
    tools=[{"type": "image_generation"}],
)

image_data = [
    output.result
    for output in response.output
    if output.type == "image_generation_call"
]

if image_data:
    with open("corgi_surfing.jpg", "wb") as f:
        f.write(base64.b64decode(image_data[0]))

curl https://api.x.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
  "model": "grok-4.7",
  "input": "Generate an image of a corgi surfing a big wave, in the style of a Japanese woodblock print",
  "tools": [
    {
      "type": "image_generation"
    }
  ]
}' | jq -r '.output[] | select(.type == "image_generation_call") | .result' \
  | base64 --decode > corgi_surfing.jpg

import base64
import os

import requests

url = "https://api.x.ai/v1/responses"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('XAI_API_KEY')}",
}
payload = {
    "model": "grok-4.7",
    "input": "Generate an image of a corgi surfing a big wave, in the style of a Japanese woodblock print",
    "tools": [{"type": "image_generation"}],
}
response = requests.post(url, headers=headers, json=payload)
data = response.json()

for item in data["output"]:
    if item["type"] == "image_generation_call":
        with open("corgi_surfing.jpg", "wb") as f:
            f.write(base64.b64decode(item["result"]))

import fs from "fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XAI_API_KEY,
  baseURL: "https://api.x.ai/v1",
});

const response = await client.responses.create({
  model: "grok-4.7",
  input:
    "Generate an image of a corgi surfing a big wave, in the style of a Japanese woodblock print",
  tools: [{ type: "image_generation" }],
});

const imageData = response.output
  .filter((output) => output.type === "image_generation_call")
  .map((output) => output.result);

if (imageData.length > 0) {
  fs.writeFileSync("corgi_surfing.jpg", Buffer.from(imageData[0], "base64"));
}

import os

from xai_sdk import Client
from xai_sdk.chat import user
from xai_sdk.tools import image_generation

client = Client(api_key=os.getenv("XAI_API_KEY"))

chat = client.chat.create(
    model="grok-4.7",
    tools=[image_generation()],
)
chat.append(user("Generate an image of a corgi surfing a big wave, in the style of a Japanese woodblock print"))
response = chat.sample()

print(response.content)
with open("image.jpeg", "wb") as f:
    f.write(response.image_outputs[0].image)

一个完整的 image_generation_call 输出项如下所示：

{
  "type": "image_generation_call",
  "id": "ig_d817cfd0-4f39-9cb3-bda2-44e538841ef2_call-a1b4dd05",
  "status": "completed",
  "prompt": "A corgi surfing a big wave, Japanese woodblock print style",
  "result": "/9j/4AAQSkZJRgABAQAAAQABAAD..."
}

其中 prompt 字段显示模型为图像模型编写的 prompt，有助于理解和调试生成内容。生成项 ID 以 ig_ 为前缀，编辑项 ID 以 ie_ 为前缀。

该工具不接受大小或格式参数；模型会为每次调用选择宽高比。如需控制，请在请求中明确说明（例如“使用 9:16 竖向宽高比”），生成图像会与之匹配。

action 参数

默认情况下，模型既可以生成新图像，也可以编辑现有图像。可选的 action 参数可以限制该行为：

操作	行为
`auto`	默认。模型可以生成和编辑图像
`generate`	仅文本生成图像
`edit`	仅图像编辑

例如，允许模型创建图像，但绝不修改对话中已有的图像：

response = client.responses.create(
    model="grok-4.7",
    input="Generate an image of a hot air balloon over the desert",
    tools=[{"type": "image_generation", "action": "generate"}],
)

curl https://api.x.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
  "model": "grok-4.7",
  "input": "Generate an image of a hot air balloon over the desert",
  "tools": [
    {
      "type": "image_generation",
      "action": "generate"
    }
  ]
}'

chat = client.chat.create(
    model="grok-4.7",
    tools=[image_generation(action="generate")],
)
chat.append(user("Generate an image of a hot air balloon over the desert"))
response = chat.sample()

编辑输入图像

当 action 设置为 edit（或使用默认的 auto）时，模型可以编辑对话中任意已有图像，包括作为输入附加的图像和之前生成的图像。编辑会生成 image_generation_call 项，其 ID 使用 ie_ 前缀。

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

response = client.responses.create(
    model="grok-4.7",
    input=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "Edit this image so it looks like a watercolor painting.",
                },
                {
                    "type": "input_image",
                    "image_url": "https://docs.x.ai/assets/api-examples/images/style-realistic.png",
                },
            ],
        }
    ],
    tools=[{"type": "image_generation", "action": "edit"}],
)

image_data = [
    output.result
    for output in response.output
    if output.type == "image_generation_call"
]

if image_data:
    with open("watercolor.jpg", "wb") as f:
        f.write(base64.b64decode(image_data[0]))

curl https://api.x.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
  "model": "grok-4.7",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Edit this image so it looks like a watercolor painting."
        },
        {
          "type": "input_image",
          "image_url": "https://docs.x.ai/assets/api-examples/images/style-realistic.png"
        }
      ]
    }
  ],
  "tools": [
    {
      "type": "image_generation",
      "action": "edit"
    }
  ]
}'

import os

from xai_sdk import Client
from xai_sdk.chat import image, user
from xai_sdk.tools import image_generation

client = Client(api_key=os.getenv("XAI_API_KEY"))

chat = client.chat.create(
    model="grok-4.7",
    tools=[image_generation(action="edit")],
)
chat.append(
    user(
        "Edit this image so it looks like a watercolor painting.",
        image("https://docs.x.ai/assets/api-examples/images/style-realistic.png"),
    )
)
response = chat.sample()

with open("image.jpeg", "wb") as f:
    f.write(response.image_outputs[0].image)

多轮编辑

之前轮次生成的图像在后续轮次中仍可编辑。继续对话时，在 xAI SDK 中将上一条响应追加到聊天，或在 Responses API 中传入 previous_response_id，模型便可参考此前的图像进一步修改：

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

response = client.responses.create(
    model="grok-4.7",
    input="Generate an image of a lighthouse on a rocky coast",
    tools=[{"type": "image_generation"}],
)

image_data = [
    output.result
    for output in response.output
    if output.type == "image_generation_call"
]

if image_data:
    with open("lighthouse.jpg", "wb") as f:
        f.write(base64.b64decode(image_data[0]))

# Follow up: edit the image from the previous turn
followup = client.responses.create(
    model="grok-4.7",
    previous_response_id=response.id,
    input="Make it night time with a full moon",
    tools=[{"type": "image_generation"}],
)

image_data_followup = [
    output.result
    for output in followup.output
    if output.type == "image_generation_call"
]

if image_data_followup:
    with open("lighthouse_night.jpg", "wb") as f:
        f.write(base64.b64decode(image_data_followup[0]))

import os

from xai_sdk import Client
from xai_sdk.chat import user
from xai_sdk.tools import image_generation

client = Client(api_key=os.getenv("XAI_API_KEY"))

chat = client.chat.create(
    model="grok-4.7",
    tools=[image_generation()],
)

# Turn 1: generate an image
chat.append(user("Generate an image of a lighthouse on a rocky coast"))
response = chat.sample()
with open("image.jpeg", "wb") as f:
    f.write(response.image_outputs[0].image)

# Turn 2: edit the image from the previous turn
chat.append(response)
chat.append(user("Make it night time with a full moon"))
followup = chat.sample()
with open("edited_image.jpeg", "wb") as f:
    f.write(followup.image_outputs[0].image)

如果不使用 previous_response_id，而是自行管理对话状态，请将上一轮的输出项（包括 image_generation_call 项）通过 input 原样传回；这些项携带的图像在下一个请求中仍可编辑。

与其他工具结合

图像生成工具可以与其他服务端工具组合。在同一请求中包含多个工具，模型会在单个智能体循环中协调它们，将一个工具的发现传给下一个。以下示例先通过 Web Search 查找事实，再根据获取的信息编写图像 prompt：

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

response = client.responses.create(
    model="grok-4.7",
    input=(
        "Find out which team won the most recent FIFA World Cup, then generate an "
        "image of a celebratory poster for that team, in a vintage travel-poster style."
    ),
    tools=[
        {"type": "web_search"},
        {"type": "image_generation"},
    ],
)

for output in response.output:
    if output.type == "web_search_call":
        print(f"Web search: {output.action}")
    elif output.type == "image_generation_call":
        print(f"Image prompt: {output.prompt}")
        with open("champions_poster.jpg", "wb") as f:
            f.write(base64.b64decode(output.result))
    elif output.type == "message":
        print(output.content[0].text)

curl https://api.x.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
  "model": "grok-4.7",
  "input": "Find out which team won the most recent FIFA World Cup, then generate an image of a celebratory poster for that team, in a vintage travel-poster style.",
  "tools": [
    {
      "type": "web_search"
    },
    {
      "type": "image_generation"
    }
  ]
}' | jq -r '.output[] | select(.type == "image_generation_call") | .result' \
  | base64 --decode > champions_poster.jpg

import os

from xai_sdk import Client
from xai_sdk.chat import user
from xai_sdk.tools import image_generation, web_search

client = Client(api_key=os.getenv("XAI_API_KEY"))

chat = client.chat.create(
    model="grok-4.7",
    tools=[web_search(), image_generation()],
)
chat.append(
    user(
        "Find out which team won the most recent FIFA World Cup, then generate an "
        "image of a celebratory poster for that team, in a vintage travel-poster style."
    )
)
response = chat.sample()

print(response.content)
with open("image.jpeg", "wb") as f:
    f.write(response.image_outputs[0].image)

# Per-tool invocation counts for the request
print(response.server_side_tool_usage)

响应输出按执行顺序交错包含工具调用：一个 web_search_call 项、一条带引用、回答事实问题的消息，以及一个携带海报的 image_generation_call 项。

相同模式也适用于 X Search、Code Execution 和自己的客户端函数。更多工具组合模式请参阅高级用法。

流式传输

流式传输时，每次图像生成调用都会发出进度事件：in_progress，然后是 generating，然后是 completed；之后发出 response.output_item.done 事件，其项携带 base64 结果。不会发出部分图像预览。

在 xAI SDK 中，传入 include=["verbose_streaming"] 可实时查看工具调用；流结束后，解码后的图像可通过累积响应中的 response.image_outputs 获取。

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

stream = client.responses.create(
    model="grok-4.7",
    input="Generate an image of an origami fox in a paper forest",
    tools=[{"type": "image_generation"}],
    stream=True,
)

for event in stream:
    if event.type.startswith("response.image_generation_call."):
        # in_progress -> generating -> completed
        print(f"Image generation status: {event.type.rsplit('.', 1)[-1]}")
    elif event.type == "response.output_item.done" and event.item.type == "image_generation_call":
        # The base64 image rides on the final output item
        with open("origami_fox.jpg", "wb") as f:
            f.write(base64.b64decode(event.item.result))
    elif event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)

import fs from "fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XAI_API_KEY,
  baseURL: "https://api.x.ai/v1",
});

const stream = await client.responses.create({
  model: "grok-4.7",
  input: "Generate an image of an origami fox in a paper forest",
  tools: [{ type: "image_generation" }],
  stream: true,
});

for await (const event of stream) {
  if (event.type.startsWith("response.image_generation_call.")) {
    // in_progress -> generating -> completed
    console.log(`Image generation status: ${event.type.split(".").pop()}`);
  } else if (
    event.type === "response.output_item.done" &&
    event.item.type === "image_generation_call"
  ) {
    // The base64 image rides on the final output item
    fs.writeFileSync(
      "origami_fox.jpg",
      Buffer.from(event.item.result, "base64")
    );
  } else if (event.type === "response.output_text.delta") {
    process.stdout.write(event.delta);
  }
}

import os

from xai_sdk import Client
from xai_sdk.chat import user
from xai_sdk.tools import get_tool_call_type, image_generation

client = Client(api_key=os.getenv("XAI_API_KEY"))

chat = client.chat.create(
    model="grok-4.7",
    tools=[image_generation()],
    include=["verbose_streaming"],
)
chat.append(user("Generate an image of an origami fox in a paper forest"))

for response, chunk in chat.stream():
    for tool_call in chunk.tool_calls:
        if get_tool_call_type(tool_call) == "image_generation_tool":
            print(f"\nGenerating image: {tool_call.function.arguments}")
    if chunk.content:
        print(chunk.content, end="", flush=True)

# The accumulated response carries the decoded images once the stream ends
with open("image.jpeg", "wb") as f:
    f.write(response.image_outputs[0].image)

图像生成，使用 images endpoint 直接生成图像
图像编辑，使用自然语言编辑图像
工具概览，所有内置工具
流式与同步，启用工具的请求的流式行为
定价，工具调用费用

最后更新：2026 年 8 月 18 日

从写代码，到创作下一幕

Agent Plan & Coding Plan

Seedance 2.5

工具

图像生成工具