带图像的生成请求（with Images）

POST

http://localhost:11434/api/generate

To submit images to multimodal models such as llava or bakllava, provide a list of base64-encoded images:

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'http://localhost:11434/api/generate' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "llava",
    "prompt": "What is in this picture?",
    "stream": false,
    "images": "string"
}'

响应示例

{
  "model": "llava",
  "created_at": "2023-11-03T15:36:02.583064Z",
  "response": "A happy cartoon character, which is cute and cheerful.",
  "done": true,
  "context": [
    1,
    2,
    3
  ],
  "total_duration": 2938432250,
  "load_duration": 2559292,
  "prompt_eval_count": 1,
  "prompt_eval_duration": 2195557000,
  "eval_count": 44,
  "eval_duration": 736432000
}

请求参数

Body 参数application/json

model

string

必需

示例值:

llava

prompt

string

必需

示例值:

What is in this picture?

stream

boolean

必需

默认值:

false

images

string

必需

图片的base64编码字符串

示例

返回响应

🟢200Success

application/json

Body

model

string

必需

created_at

string

必需

response

string

必需

done

boolean

必需

context

array[integer]

必需

total_duration

integer

必需

load_duration

integer

必需

prompt_eval_count

integer

必需

prompt_eval_duration

integer

必需

eval_count

integer

必需

eval_duration

integer

必需

修改于 2025-03-26 10:17:12

JSON 模式请求（JSON Mode）

原始模式请求（Raw Mode）