# Google Imagen ## 1. 概述 google推出的文生图模型。 **模型列表：** * `imagegeneration@002` * `imagegeneration@005` * `imagegeneration@006` * `imagen-3.0-generate-001` * `imagen-3.0-generate-002` * `imagen-3.0-fast-generate-001` > **说明：** > > 1. 该系列模型对中文支持不太友好，使用自然语言描述时尽量使用英文 ## 2. 请求说明 * **请求方法**:`POST` * **请求地址**: > `https://gateway.theturbo.ai/v1/images/generations` *** ## 3. 请求参数 ### 3.1 Header 参数 | 参数名称 | 类型 | 必填 | 说明 | 示例值 | | --------------- | ------ | -- | ------------------------------------------ | ---------------------- | | `Content-Type` | string | 是 | 设置请求头类型，必须为 `application/json` | `application/json` | | `Accept` | string | 是 | 设置响应类型，建议统一为 `application/json` | `application/json` | | `Authorization` | string | 是 | 身份验证所需的 API\_KEY，格式 `Bearer $YOUR_API_KEY` | `Bearer $YOUR_API_KEY` | *** ### 3.2 Body 参数 (application/json)
参数名称类型必填说明示例（默认值）
modelstring是要使用的模型 ID。详见概述列出的可用版本，如 imagen-3.0-generate-001。imagen-3.0-generate-001
promptstring是一段描述所需图像的文字。imagen-3.0 描述最大长度为 480 词元。 imagegeneration@005 imagegeneration@006 描述最大长度为 128 词元。 imagegeneration@002 描述最大长度为 128 词元。A cute baby sea otter
nnumber否生成图像的数量，必须在 1 到 4 之间。1
aspect_ratiostring否图片的宽高比。支持1:1 9:16 16:9 3:4 4:3。不同模型支持的略有差异。1:1
output_formatstring否生成图像的格式。支持png jpeg。png
stylestring否生成图像的风格。支持photograph digital_art landscape sketch watercolor cyberpunk pop_art。此参数仅适用于imagegeneration@002。photograph
response_formatstring否生成的图像返回的格式。只支持b64_json。b64_json
*** ## 4. 请求示例 {% tabs %} {% tab title="HTTP" %} ```http POST /v1/images/generations Content-Type: application/json Accept: application/json Authorization: Bearer $YOUR_API_KEY { "model": "imagen-3.0-generate-001", "prompt": "A cute baby sea otter", "n": 1, "aspect_ratio": "1:1" } ``` {% endtab %} {% tab title="Shell" %} ```sh curl https://gateway.theturbo.ai/v1/images/generations \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ -H "Authorization: Bearer $YOUR_API_KEY" \ -d "{ \"model\": \"imagen-3.0-generate-001\", \"prompt\": \"A cute baby sea otter\", \"n\": 1, \"aspect_ratio\": \"1:1\" }" ``` {% endtab %} {% tab title="Go" %} ```go package main import ( "encoding/base64" "encoding/json" "fmt" "io/ioutil" "net/http" "os" "strings" ) const ( YOUR_API_KEY = "sk-123456789012345678901234567890123456789012345678" REQUEST_PAYLOAD = `{ "model": "imagen-3.0-generate-001", "prompt": "A cute baby sea otter", "n": 1, "aspect_ratio": "1:1" }` EXAMPLE_FILE_PATH = "example.png" ) type Data struct { B64Json string `json:"b64_json"` } type ResponseJSON struct { Data []Data `json:"data"` } func main() { requestURL := "https://gateway.theturbo.ai/v1/images/generations" requestMethod := "POST" requestPayload := strings.NewReader(REQUEST_PAYLOAD) req, err := http.NewRequest(requestMethod, requestURL, requestPayload) if err != nil { fmt.Println("Create request failed, err: ", err) return } req.Header.Add("Content-Type", "application/json") req.Header.Add("Accept", "application/json") req.Header.Add("Authorization", "Bearer "+YOUR_API_KEY) client := &http.Client{} resp, err := client.Do(req) if err != nil { fmt.Println("Do request failed, err: ", err) return } defer resp.Body.Close() respBodyBytes, err := ioutil.ReadAll(resp.Body) if err != nil { fmt.Println("Read response body failed, err: ", err) return } if resp.StatusCode != 200 { fmt.Printf("status code: %d\n", resp.StatusCode) fmt.Println(string(respBodyBytes)) return } var responseJSON ResponseJSON if err := json.Unmarshal(respBodyBytes, &responseJSON); err != nil { fmt.Println("Parse response body failed, err: ", err) return } if len(responseJSON.Data) == 0 || responseJSON.Data[0].B64Json == "" { fmt.Println("Parse response body failed, err: empty b64_json") return } imageData, err := base64.StdEncoding.DecodeString(responseJSON.Data[0].B64Json) if err != nil { fmt.Println("Parse b64_json failed, err: ", err) return } imageFile, err := os.Create(EXAMPLE_FILE_PATH) if err != nil { fmt.Printf("Create file %s failed, err: %v\n", EXAMPLE_FILE_PATH, err) return } if _, err := imageFile.Write(imageData); err != nil { fmt.Printf("Write to file %s failed, err: %v\n", EXAMPLE_FILE_PATH, err) imageFile.Close() return } imageFile.Close() fmt.Println("success to write to file ", EXAMPLE_FILE_PATH) } ``` {% endtab %} {% endtabs %} ## 5. 响应示例 ```json { "created": 1589478378, "data": [ { "b64_json": "..." }, { "b64_json": "..." } ] } ``` --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.console.zenlayer.com/test/hotfix/aigw/image-generation/google-imagen-image-generation.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.