Skip to main content
Glama

image_create

图片生成 / 编辑

每次调用固定生成 1 张。 默认异步:返回 workspace_id(status=pending,result_type=image),用 work/status 轮询取 result_url; sync_mod=true 时同步阻塞到出图,响应里 result_url 直接为图片 URL(status=completed)。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "image_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo可选。默认 `nanobanana-pro`。
ratioNo取值集因 model 而异,详见请求体表格。
promptNo生成 / 编辑指令
sync_modNo`true` 同步阻塞到出图(最长约 60 秒);默认 `false` 异步返回 `workspace_id`。
backgroundNo背景,只有 `seedream-5.5` 收:`transparent` 透明底(出 png)、`opaque` 不透明、`auto` 由模型决定;不传 = `auto`。其他模型传了报参数错。
image_urlsNo文生图时为空数组;编辑时非空,上限因 model 而异。
resolutionNo除 `seedream-5.0-lite` 外都支持;取值集和默认值详见请求体表格。
callback_idNo自定义追踪 ID,在响应中原样回传
idempotency_keyNo幂等键(预留字段,当前服务端未对本接口做去重)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / description
      Previous value: -"图片生成或编辑。`model` 为模型短名称,省略时服务端默认 `nanobanana-pro`。\n文生图:`image_urls` 为空;图片编辑:`image_urls` 非空。每次固定生成 1 张。\n\n**模式支持**:\n- 仅文生图:`grok-2-image`\n- 仅编辑:`grok-imagine-image`\n- 文生 + 编辑:`nanobanana-pro`、`nano-banana-2`、`nano-banana-2-fast`、`seedream-5.0-pro`、`seedream-5.0-lite`、`gpt-image-2`\n\n**参数支持(按模型不同,服务端校验为准)**:\n\n| model | ratio | resolution | 编辑输入图上限 |\n|---|---|---|---|\n| `nanobanana-pro` | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 21:9 / 1:4 / 4:1 | 1k / 2k / 4k / 8k | 14 |\n| `nano-banana-2` | 同上 + 1:8 / 8:1 | 0.5k / 1k / 2k / 4k | 14 |\n| `nano-banana-2-fast` | 同上 + 1:8 / 8:1 | 2k / 4k | 14 |\n| `seedream-5.0-pro` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9 | 2k(默认)/ 1k | 10 |\n| `seedream-5.0-lite` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 1:4 / 4:1 / 1:8 / 8:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 9:21 / 21:9 | — | 10 |\n| `gpt-image-2` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9 | 1k / 2k / 4k | 10 |\n| `grok-2-image` | 不校验 | — | 不支持编辑 |\n| `grok-imagine-image` | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9 | — | 1 |\n\n- `ratio` 留空由模型按 prompt 决定;prompt 内写明的比例(如 `16:9`、「竖屏」)优先于 `ratio` 参数。\n- `resolution` 不支持的模型必须留空;`4k` 及以上需订阅身份。\n- `image_urls` 只收 http(s) URL,不收 data URI;单张像素 ≤ 3600 万。\n"New value: +"图片生成或编辑。`model` 为模型短名称,省略时服务端默认 `nanobanana-pro`。\n文生图:`image_urls` 为空;图片编辑:`image_urls` 非空。每次固定生成 1 张。\n\n**模式支持**:\n- 下表模型都支持文生图和编辑;传其他 model 返回 `ret=10000`,`msg` 为 `unsupported model \"<传入值>\"; supported models: <可选值,逗号分隔>`,不扣积分。\n\n**参数支持(按模型不同,服务端校验为准)**:\n\n比例集合(表里用代号):\n- A:1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9\n- B:1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 21:9 / 1:4 / 4:1\n- C:B + 1:8 / 8:1\n- D:1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 1:4 / 4:1 / 1:8 / 8:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 9:21 / 21:9\n- E:1:1 / 16:9 / 9:16 / 4:3 / 3:4 / 3:2 / 2:3 / 2:1 / 1:2 / 19.5:9 / 9:19.5 / 20:9 / 9:20\n\n| model | ratio | resolution(第一个为默认) | 编辑输入图上限 |\n|---|---|---|---|\n| `gpt-image-2` | A | 1k / 2k / 4k | 10 |\n| `gpt-image-2.5` | A | 1k / 2k / 4k | 16 |\n| `gpt-image-2.5-sunburst` | A | 1k / 2k / 4k | 16 |\n| `nano-banana-2` | C | 0.5k / 1k / 2k / 4k | 14 |\n| `nano-banana-2.1` | C | 1k / 2k / 4k | 14 |\n| `nano-banana-2-fast` | C | 2k / 4k | 14 |\n| `nanobanana-pro` | B | 1k / 2k / 4k / 8k | 14 |\n| `seedream-5.0-lite` | D | — | 10 |\n| `seedream-5.0-pro` | A | 2k / 1k | 10 |\n| `seedream-5.5` | A | 2k / 1k / 1.5k / 3k | 10 |\n| `grok-imagine-image-2.0` | E | 2k / 1k | 3 |\n\n- `ratio` 留空由模型按 prompt 决定;prompt 内写明的比例(如 `16:9`、「竖屏」)优先于 `ratio` 参数。\n- `resolution` 不传按上表第一个值;不支持的模型(`seedream-5.0-lite`)必须留空;`4k` 及以上需订阅身份。\n- 本接口不收 `quality`:`gpt-image-2` / `gpt-image-2.5` / `gpt-image-2.5-sunburst` / `grok-imagine-image-2.0` 固定按 `medium` 出图。\n- `background` 只有 `seedream-5.5` 收:`transparent` 出透明底 png,`opaque` 不透明,`auto` 或不传由模型决定;其他模型传了报参数错(`ret=10000`)。\n- `image_urls` 只收 http(s) URL,不收 data URI;单张像素 ≤ 3600 万。\n- 参考图链接 404 时同步返回 `ret=60809`(`msg` 指明第几张),不扣积分,不建任务;上传的文件请原样使用上传接口返回的 `data.url`。\n"
    • addedInput schema / properties / background
      Added value: +{
      +  "description": "背景,只有 `seedream-5.5` 收:`transparent` 透明底(出 png)、`opaque` 不透明、`auto` 由模型决定;不传 = `auto`。其他模型传了报参数错。\n",
      +  "enum": [
      +    "auto",
      +    "transparent",
      +    "opaque"
      +  ],
      +  "example": "transparent",
      +  "type": "string"
      +}
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "nanobanana-pro",
      -  "nano-banana-2",
      -  "nano-banana-2-fast",
      -  "seedream-5.0-pro",
      -  "seedream-5.0-lite",
      -  "gpt-image-2",
      -  "grok-2-image",
      -  "grok-imagine-image"
      -]New value: +[
      +  "gpt-image-2",
      +  "gpt-image-2.5",
      +  "gpt-image-2.5-sunburst",
      +  "nano-banana-2",
      +  "nano-banana-2.1",
      +  "nano-banana-2-fast",
      +  "nanobanana-pro",
      +  "seedream-5.0-lite",
      +  "seedream-5.0-pro",
      +  "seedream-5.5",
      +  "grok-imagine-image-2.0"
      +]
    • changedInput schema / properties / ratio / enum
      Previous value: -[
      -  "1:1",
      -  "1:2",
      -  "2:1",
      -  "1:3",
      -  "3:1",
      -  "1:4",
      -  "4:1",
      -  "1:8",
      -  "8:1",
      -  "2:3",
      -  "3:2",
      -  "3:4",
      -  "4:3",
      -  "4:5",
      -  "5:4",
      -  "5:7",
      -  "7:5",
      -  "9:16",
      -  "16:9",
      -  "9:21",
      -  "21:9"
      -]New value: +[
      +  "1:1",
      +  "1:2",
      +  "2:1",
      +  "1:3",
      +  "3:1",
      +  "1:4",
      +  "4:1",
      +  "1:8",
      +  "8:1",
      +  "2:3",
      +  "3:2",
      +  "3:4",
      +  "4:3",
      +  "4:5",
      +  "5:4",
      +  "5:7",
      +  "7:5",
      +  "9:16",
      +  "16:9",
      +  "9:21",
      +  "21:9",
      +  "19.5:9",
      +  "9:19.5",
      +  "20:9",
      +  "9:20"
      +]
    • changedInput schema / properties / resolution / description
      Previous value: -"仅 `nanobanana-pro` / `nano-banana-2` / `nano-banana-2-fast` / `seedream-5.0-pro` / `gpt-image-2` 支持;取值集详见请求体表格。\n"New value: +"除 `seedream-5.0-lite` 外都支持;取值集和默认值详见请求体表格。\n"
    • changedInput schema / properties / resolution / enum
      Previous value: -[
      -  "0.5k",
      -  "1k",
      -  "2k",
      -  "4k",
      -  "8k"
      -]New value: +[
      +  "0.5k",
      +  "1k",
      +  "1.5k",
      +  "2k",
      +  "3k",
      +  "4k",
      +  "8k"
      +]
  2. Changed13 schema fields changed
    • changedInput schema / description
      Previous value: -"图片生成或编辑。`model` 为模型短名称,省略时服务端默认 `nanobanana-pro`。\n文生图:`image_urls` 为空;图片编辑:`image_urls` 非空。\n\n**模式支持**:\n- 仅文生图:`grok-2-image`\n- 仅编辑:`seedream-4.5-seq`、`seedream-5.0-lite-seq`、`grok-imagine-image`\n- 文生 + 编辑:`nanobanana-pro`、`nano-banana-2`、`nano-banana-2-fast`、`seedream-4.5`、`seedream-5.0-lite`、`gpt-image-2`\n\n**参数支持(按模型不同)**:\n- `ratio` 支持值因模型而异:\n  - `nanobanana-pro` / `nano-banana-2` / `nano-banana-2-fast`: `16:9` / `1:1` / `9:16` / `21:9` / `2:3` / `3:2`\n  - `seedream-4.5` / `seedream-4.5-seq` / `seedream-5.0-lite` / `seedream-5.0-lite-seq`: `16:9` / `1:1` / `9:16` / `2:3` / `3:2`\n  - `gpt-image-2`: `1:1` / `3:2` / `2:3` / `3:4` / `4:3` / `4:5` / `5:4` / `9:16` / `16:9` / `21:9`\n  - `grok-2-image` / `grok-imagine-image`: 不校验\n- `resolution` 仅以下模型支持,且取值集不同:\n  - `nanobanana-pro`: `1k` / `2k` / `4k` / `8k`\n  - `nano-banana-2`: `0.5k` / `1k` / `2k` / `4k`\n  - `nano-banana-2-fast`: `2k` / `4k`\n  - `gpt-image-2`: `1k` / `2k`\n- `quality` 仅 `gpt-image-2` 支持,取值:`low` / `medium` / `high`\n- `num_images` 仅 `seedream-4.5-seq` / `seedream-5.0-lite-seq` 支持,上限 15\n"New value: +"图片生成或编辑。`model` 为模型短名称,省略时服务端默认 `nanobanana-pro`。\n文生图:`image_urls` 为空;图片编辑:`image_urls` 非空。每次固定生成 1 张。\n\n**模式支持**:\n- 仅文生图:`grok-2-image`\n- 仅编辑:`grok-imagine-image`\n- 文生 + 编辑:`nanobanana-pro`、`nano-banana-2`、`nano-banana-2-fast`、`seedream-5.0-pro`、`seedream-5.0-lite`、`gpt-image-2`\n\n**参数支持(按模型不同,服务端校验为准)**:\n\n| model | ratio | resolution | 编辑输入图上限 |\n|---|---|---|---|\n| `nanobanana-pro` | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 21:9 / 1:4 / 4:1 | 1k / 2k / 4k / 8k | 14 |\n| `nano-banana-2` | 同上 + 1:8 / 8:1 | 0.5k / 1k / 2k / 4k | 14 |\n| `nano-banana-2-fast` | 同上 + 1:8 / 8:1 | 2k / 4k | 14 |\n| `seedream-5.0-pro` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9 | 2k(默认)/ 1k | 10 |\n| `seedream-5.0-lite` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 1:4 / 4:1 / 1:8 / 8:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 5:7 / 7:5 / 9:16 / 16:9 / 9:21 / 21:9 | — | 10 |\n| `gpt-image-2` | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9 | 1k / 2k / 4k | 10 |\n| `grok-2-image` | 不校验 | — | 不支持编辑 |\n| `grok-imagine-image` | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9 | — | 1 |\n\n- `ratio` 留空由模型按 prompt 决定;prompt 内写明的比例(如 `16:9`、「竖屏」)优先于 `ratio` 参数。\n- `resolution` 不支持的模型必须留空;`4k` 及以上需订阅身份。\n- `image_urls` 只收 http(s) URL,不收 data URI;单张像素 ≤ 3600 万。\n"
    • addedInput schema / properties / callback_id
      Added value: +{
      +  "description": "自定义追踪 ID,在响应中原样回传",
      +  "type": "string"
      +}
    • removedInput schema / properties / concurrency
      Removed value: -{
      -  "description": "并发数,控制一次性输出的结果数量",
      -  "example": 1,
      -  "format": "int32",
      -  "type": "integer"
      -}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "幂等键(预留字段,当前服务端未对本接口做去重)",
      +  "type": "string"
      +}
    • changedInput schema / properties / image_urls / description
      Previous value: -"文生图时为空数组;编辑时非空。\n"New value: +"文生图时为空数组;编辑时非空,上限因 model 而异。\n"
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "nanobanana-pro",
      -  "nano-banana-2",
      -  "nano-banana-2-fast",
      -  "seedream-4.5",
      -  "seedream-4.5-seq",
      -  "seedream-5.0-lite",
      -  "seedream-5.0-lite-seq",
      -  "gpt-image-2",
      -  "grok-2-image",
      -  "grok-imagine-image"
      -]New value: +[
      +  "nanobanana-pro",
      +  "nano-banana-2",
      +  "nano-banana-2-fast",
      +  "seedream-5.0-pro",
      +  "seedream-5.0-lite",
      +  "gpt-image-2",
      +  "grok-2-image",
      +  "grok-imagine-image"
      +]
    • removedInput schema / properties / num_images
      Removed value: -{
      -  "description": "仅 `seedream-4.5-seq` / `seedream-5.0-lite-seq` 支持,单次输出图片数量。",
      -  "format": "int32",
      -  "maximum": 15,
      -  "minimum": 1,
      -  "type": "integer"
      -}
    • changedInput schema / properties / prompt / description
      Previous value: -"文生图提示词"New value: +"生成 / 编辑指令"
    • removedInput schema / properties / quality
      Removed value: -{
      -  "description": "仅 `gpt-image-2` 支持。",
      -  "enum": [
      -    "low",
      -    "medium",
      -    "high"
      -  ],
      -  "type": "string"
      -}
    • changedInput schema / properties / ratio / description
      Previous value: -"取值集因 model 而异,详见请求体描述。"New value: +"取值集因 model 而异,详见请求体表格。"
    • changedInput schema / properties / ratio / enum
      Previous value: -[
      -  "1:1",
      -  "3:2",
      -  "2:3",
      -  "3:4",
      -  "4:3",
      -  "4:5",
      -  "5:4",
      -  "16:9",
      -  "9:16",
      -  "21:9"
      -]New value: +[
      +  "1:1",
      +  "1:2",
      +  "2:1",
      +  "1:3",
      +  "3:1",
      +  "1:4",
      +  "4:1",
      +  "1:8",
      +  "8:1",
      +  "2:3",
      +  "3:2",
      +  "3:4",
      +  "4:3",
      +  "4:5",
      +  "5:4",
      +  "5:7",
      +  "7:5",
      +  "9:16",
      +  "16:9",
      +  "9:21",
      +  "21:9"
      +]
    • changedInput schema / properties / resolution / description
      Previous value: -"仅 `nanobanana-pro` / `nano-banana-2` / `nano-banana-2-fast` / `gpt-image-2` 支持;取值集详见请求体描述。\n"New value: +"仅 `nanobanana-pro` / `nano-banana-2` / `nano-banana-2-fast` / `seedream-5.0-pro` / `gpt-image-2` 支持;取值集详见请求体表格。\n"
    • addedInput schema / properties / sync_mod / description
      Added value: +"`true` 同步阻塞到出图(最长约 60 秒);默认 `false` 异步返回 `workspace_id`。"
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare the generic write/open-world/non-idempotent profile; the description goes further by disclosing the async job model, the pending status and result_type returned, the required polling step, and the blocking alternative with a direct result_url. This is the key behavior an agent cannot get from annotations, though polling cadence and failure handling are left to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: what it does, output cardinality, then default-async behavior followed by the sync escape hatch. Nothing is redundant and the most consequential fact (async by default, poll for the result) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly spends its space describing the return shape (workspace_id/status=pending vs. result_url/status=completed) and names the polling path. For a 9-parameter tool this is close to sufficient; it could add how often to poll or that errors do not create a job, but the schema covers those edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself is unusually rich (per-model ratio sets, resolution defaults, background restrictions, error codes), so the schema already carries parameter meaning. The description mainly restates sync_mod's outcome (workspace_id vs. direct result_url), adding only marginal value beyond the schema's own sync_mod text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening '图片生成 / 编辑' names a concrete verb pair and the resource, and '每次调用固定生成 1 张' pins the output cardinality. It does not, however, distinguish this tool from sibling image tools such as image_enhance, image_poster, or image_cutout, so an agent must infer that this is the general-purpose generation/editing entry point.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is focused on invocation mode rather than tool selection: the definition states the default is asynchronous (poll via work/status) and that sync_mod=true blocks until the image is ready. That is actionable for how to drive the call, but there is no when-to-use / when-not-to-use guidance relative to the many sibling image tools, which is exactly what an agent selecting among 30 siblings needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources