Skip to main content
Nano Banana Pro 的 API 参考。Nano Banana Pro(Gemini 3 Pro Image)是 Google Nano Banana 图像生成家族的 Pro 层级,面向复杂场景和清晰可读的文字。

快速开始

你的 Comfy 工作区中创建一个密钥,并将其导出为 COMFY_API_KEY。Python 和 TypeScript 代码片段使用 Comfy SDK(pip install comfy-sdknpm install @comfyorg/sdk);cURL 代码片段是通过原始 HTTP 进行的相同调用。 模型 ID: vertexai/gemini-3-pro-image 端点: POST https://api.comfy.org/v2/models/vertexai/gemini-3-pro-image

Schema

Input

object[]
必填
The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.
object[]
必填
object
URI based data.
string
URI
string
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values: application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webm
object
Inline data in raw bytes. For gemini-2.0-flash-lite and gemini-2.0-flash, you can specify up to 3000 images by using inlineData.
string (byte)
The base64 encoding of the image, PDF, or video to include inline in the prompt. When including media inline, you must also specify the media type (mimeType) of the data. Size limit: 20MBFormat: byte
string
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values: application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webm
string
模型读取该部分视频的方式。设置为 “AGENTIC” 可让模型自行决定要检查的片段,而不是按固定速率采样帧。使用默认的固定速率采样时请省略。在 gemini-3.7-flash 及更新的 Flash 模型上受支持。
string
A text prompt or code snippet.
boolean
Indicates this part is a thinking/reasoning step from the model.
string
Possible values: user, model
object
Sampling, length and output settings for the generation. Every field is optional: the fields below that declare a default apply it when omitted, and the rest fall back to the model’s own behaviour.
object
Configuration for image generation
string
Aspect ratio for generated images
object
Optional. The image output format for generated images.
integer
Optional. The compression quality of the output image.
string
Optional. The image format that the output should be saved as.
string
Optional. Specifies the size of generated images. Supported values are 1K, 2K, 4K. If not specified, the model will use default value 1K.
integer
Maximum number of tokens that can be generated in the response. A token is approximately 4 characters. 100 tokens correspond to roughly 60-80 words.Range: 16 to 65536
`TEXT`, `IMAGE`[]
integer
When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn’t guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. Available for the following models:, gemini-2.5-flash, gemini-2.5-pro, gemini-2.5-flash-preview-04-1, gemini-2.5-pro-preview-05-0, gemini-2.0-flash-lite-00, gemini-2.0-flash-001
string[]
number
默认值:"1"
The temperature is used for sampling during response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected. In this case, responses for a given prompt are mostly deterministic, but a small amount of variation is still possible. If the model returns a response that’s too generic, too short, or the model gives a fallback response, try increasing the temperatureRange: 0 to 2Format: float
object
Optional. Configuration for thinking features. Thinking is a process where the model breaks down a complex task into smaller steps to generate a higher-quality response.
boolean
Optional. If true, the model will include its thoughts in the response.
integer
Optional. The token budget for the model’s thinking process. The model will make a best effort to stay within this budget.
string
Optional. The thinking level for the model.Possible values: THINKING_LEVEL_UNSPECIFIED, LOW, MEDIUM, HIGH, MINIMAL
integer
默认值:"40"
Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model’s vocabulary. A top-K of 3 means that the next token is selected from among the 3 most probable tokens by using temperature.Range: 1 to
number
默认值:"0.95"
If specified, nucleus sampling is used. Top-P changes how the model selects tokens for output. Tokens are selected from the most (see top-K) to least probable until the sum of their probabilities equals the top-P value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-P value is 0.5, then the model will select either A or B as the next token by using temperature and excludes C as a candidate. Specify a lower value for less random responses and a higher value for more random responses.Range: 0 to 1Format: float
object[]
Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
string
必填
Possible values: HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENT
string
必填
Possible values: OFF, BLOCK_NONE, BLOCK_LOW_AND_ABOVE, BLOCK_MEDIUM_AND_ABOVE, BLOCK_ONLY_HIGH
object
Instructions for the model to steer it toward better performance. For example, “Answer as concisely as possible” or “Don’t use technical terms in your response”. The text strings count toward the token limit. The role field of systemInstruction is ignored and doesn’t affect the performance of the model. Note: Only text should be used in parts and content in each part should be in a separate paragraph.
object[]
必填
A list of ordered parts that make up a single message. Different parts may have different IANA MIME types. For limits on the inputs, such as the maximum number of tokens or the number of images, see the model specifications on the Google models page.
string
A text prompt or code snippet.
string
The identity of the entity that creates the message. The following values are supported: user: This indicates that the message is sent by a real person, typically a user-generated message. model: This indicates that the message is generated by the model. The model value is used to insert messages from the model into the conversation during multi-turn conversations. For non-multi-turn conversations, this field can be left blank or unset.Possible values: user, model
object[]
A piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. See Function calling.
object[]
string
string
必填
object
JSON schema for the function parameters
boolean
If true, generated images will be uploaded to cloud storage and returned as signed URLs instead of inline base64 data. The URLs expire after 24 hours.
object
For video input, the start and end offset of the video in Duration format. For example, to specify a 10 second clip starting at 1:00, set “startOffset”: { “seconds”: 60 } and “endOffset”: { “seconds”: 70 }. The metadata should only be specified while the video data is presented in inlineData or fileData.
object
Represents a duration offset for video timeline positions.
integer
Signed fractions of a second at nanosecond resolution. Negative second values with fractions must still have non-negative nanos values.Range: 0 to 999999999
integer
Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive.Range: -315576000000 to 315576000000
object
Represents a duration offset for video timeline positions.
integer
Signed fractions of a second at nanosecond resolution. Negative second values with fractions must still have non-negative nanos values.Range: 0 to 999999999
integer
Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive.Range: -315576000000 to 315576000000
Generated from the schema Router serves at GET /v2/models/vertexai/gemini-3-pro-image/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

object[]
object
object[]
string[]
integer
string
string (date)
Format: date
integer
string
string
object
The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.
object[]
必填
object
URI based data.
string
URI
string
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values: application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webm
object
Inline data in raw bytes. For gemini-2.0-flash-lite and gemini-2.0-flash, you can specify up to 3000 images by using inlineData.
string (byte)
The base64 encoding of the image, PDF, or video to include inline in the prompt. When including media inline, you must also specify the media type (mimeType) of the data. Size limit: 20MBFormat: byte
string
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values: application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webm
string
模型读取该部分视频的方式。设置为 “AGENTIC” 可让模型自行决定要检查的片段,而不是按固定速率采样帧。使用默认的固定速率采样时请省略。在 gemini-3.7-flash 及更新的 Flash 模型上受支持。
string
A text prompt or code snippet.
boolean
Indicates this part is a thinking/reasoning step from the model.
string
Possible values: user, model
string
object[]
string
Possible values: HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENT
string
The probability that the content violates the specified safety categoryPossible values: NEGLIGIBLE, LOW, MEDIUM, HIGH, UNKNOWN
string
Timestamp when the response was created.
string
The model version used to generate the response.
object
string
string
object[]
string
Possible values: HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENT
string
The probability that the content violates the specified safety categoryPossible values: NEGLIGIBLE, LOW, MEDIUM, HIGH, UNKNOWN
string
Unique identifier for the response.
object
integer
Output only. Number of tokens in the cached part in the input (the cached content).
integer
Number of tokens in the response(s).
object[]
Breakdown of candidate tokens by modality.
string
Type of input or output content modality.Possible values: MODALITY_UNSPECIFIED, TEXT, IMAGE, VIDEO, AUDIO, DOCUMENT
integer
Number of tokens for the given modality.
integer
Number of tokens in the request. When cachedContent is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
object[]
Breakdown of prompt tokens by modality.
string
Type of input or output content modality.Possible values: MODALITY_UNSPECIFIED, TEXT, IMAGE, VIDEO, AUDIO, DOCUMENT
integer
Number of tokens for the given modality.
integer
Number of tokens present in thoughts output.
integer
Number of tokens present in tool-use prompt(s).
object[]
按模态细分的工具使用提示 token。
string
输入或输出内容模态的类型。可能的值:MODALITY_UNSPECIFIEDTEXTIMAGEVIDEOAUDIODOCUMENT
integer
给定模态的 token 数量。
integer
Total number of tokens (prompt + candidates).
string
Traffic type used for the request (e.g., PROVISIONED_THROUGHPUT).

示例

输入

输出

默认情况下,已生成图像的 part 会在 inlineData.data 中包含 base64 字节,并在 inlineData.mimeType 中包含媒体类型。请解码这些字节并将其保存到文件中。使用 uploadImagesToStorage: true 时,上传的图像则改用 fileData.fileUri 提供签名 URL,并用 fileData.mimeType 表示媒体类型。请在 URL 过期之前下载这些图像,即创建后 24 小时内。上传失败会使该图像保持内联形式,因此请检查每个 part 中的 inlineDatafileData;文本 part 也可能出现,并且图像不保证是第一个 part。

发布前须知

SDK 会生成 Idempotency-Key 并在自动重试中复用它。手动重试时,请复用原始 key。Router 最长可保持连接 10 分钟。 请求失败时,Router 会发送 X-Comfy-Error-Type 响应头说明原因。422 表示 Router 在调用提供商之前就拒绝了输入。生成的资源请及时下载,因为结果链接会过期

请求头

身份验证、幂等性、请求 ID、错误分类、重试节奏、消费限额。

使用 Router API

模型发现、校验错误、重试与计费。

限制

Router 目前不支持的功能,以及替代方案。