Image Generate | Venice API Docs

/api/v1/image/generate

curl --request POST \
  --url https://api.venice.ai/api/v1/image/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "grok-imagine-image",
  "prompt": "A beautiful sunset over a mountain range",
  "cfg_scale": 7.5,
  "embed_exif_metadata": false,
  "format": "webp",
  "height": 1024,
  "hide_watermark": false,
  "inpaint": "<unknown>",
  "lora_strength": 50,
  "negative_prompt": "Clouds, Rain, Snow",
  "return_binary": false,
  "variants": 3,
  "safe_mode": false,
  "seed": 123456789,
  "steps": 8,
  "style_preset": "3D Model",
  "aspect_ratio": "1:1",
  "resolution": "1K",
  "quality": "high",
  "enable_web_search": false,
  "width": 1024
}
'

{
  "id": "generate-image-1234567890",
  "images": [
    "<string>"
  ],
  "timing": {
    "inferenceDuration": 123,
    "inferencePreprocessingTime": 123,
    "inferenceQueueTime": 123,
    "total": 123
  },
  "request": "<unknown>"
}

POST

image

generate

/api/v1/image/generate

curl --request POST \
  --url https://api.venice.ai/api/v1/image/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "grok-imagine-image",
  "prompt": "A beautiful sunset over a mountain range",
  "cfg_scale": 7.5,
  "embed_exif_metadata": false,
  "format": "webp",
  "height": 1024,
  "hide_watermark": false,
  "inpaint": "<unknown>",
  "lora_strength": 50,
  "negative_prompt": "Clouds, Rain, Snow",
  "return_binary": false,
  "variants": 3,
  "safe_mode": false,
  "seed": 123456789,
  "steps": 8,
  "style_preset": "3D Model",
  "aspect_ratio": "1:1",
  "resolution": "1K",
  "quality": "high",
  "enable_web_search": false,
  "width": 1024
}
'

{
  "id": "generate-image-1234567890",
  "images": [
    "<string>"
  ],
  "timing": {
    "inferenceDuration": 123,
    "inferencePreprocessingTime": 123,
    "inferenceQueueTime": 123,
    "total": 123
  },
  "request": "<unknown>"
}

尺寸选项

图像模型使用模型专属的尺寸参数：

基于像素的模型接受 width 和 height，例如 venice-sd35 和 qwen-image。
基于宽高比的模型接受 aspect_ratio，例如 qwen-image-2。
基于分辨率等级的模型同时接受 aspect_ratio 和 resolution。

例如，gpt-image-2、nano-banana-2 和 nano-banana-pro 支持 resolution 取值 1K、2K 和 4K：

{
  "model": "gpt-image-2",
  "prompt": "a cinematic wide shot of Venice at sunset",
  "aspect_ratio": "16:9",
  "resolution": "4K",
  "format": "png"
}

相同的分辨率分级尺寸模式也适用于 Nano Banana 模型：

{
  "model": "nano-banana-pro",
  "prompt": "a serene canal in venice at sunset",
  "aspect_ratio": "16:9",
  "resolution": "2K"
}

对于接受宽高比但不公开分辨率等级的模型，请发送 aspect_ratio 而不带 resolution：

{
  "model": "qwen-image-2",
  "prompt": "a serene canal in venice at sunset",
  "aspect_ratio": "16:9"
}

对于使用直接像素尺寸的模型，请改为发送 width 和 height：

{
  "model": "venice-sd35",
  "prompt": "a serene canal in venice at sunset",
  "width": 1024,
  "height": 1024
}

在跨模型混用尺寸字段之前，请查看图像模型或 Models 端点了解每个模型支持的尺寸选项。

质量等级

部分模型接受可选的 quality 参数（low、medium、high），用于在视觉保真度和成本之间取得平衡。当前由 gpt-image-2 支持；其他模型会忽略该参数。

{
  "model": "gpt-image-2",
  "prompt": "a cinematic wide shot of Venice at sunset",
  "aspect_ratio": "16:9",
  "resolution": "2K",
  "quality": "medium"
}

当您省略 quality 时，模型将使用其默认等级（gpt-image-2 为 high）。价格取决于 resolution 与 quality 的组合 —— gpt-image-2 的各等级价格（1K/2K/4K × low/medium/high）在 Models 端点的 model_spec.pricing.quality 下公开，也列于定价概览中。

质量感知定价是所有 API 和 SDK 调用方的默认行为 —— 无需显式启用的请求头。省略 quality 的请求按模型的默认等级（gpt-image-2 为 high）计费。

Postman 集合

如需更多示例，请参阅此 Postman 集合。

授权

Authorization

string

header

必填

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

请求头

Accept-Encoding

string

Supported compression encodings (gzip, br). Only applied when return_binary is false.

示例:

"gzip, br"

请求体

application/json

model

string

必填

The model to use for image generation.

示例:

"grok-imagine-image"

prompt

string

必填

The description for the image. Character limit is model specific and is listed in the promptCharacterLimit setting in the model list endpoint.

Required string length: 1 - 7500

示例:

"A beautiful sunset over a mountain range"

cfg_scale

number

CFG scale parameter. Higher values lead to more adherence to the prompt.

必填范围: 0 < x <= 20

示例:

7.5

embed_exif_metadata

boolean

默认值:false

Embed prompt generation information into the image's EXIF metadata.

示例:

false

format

enum<string>

默认值:webp

The image format to return. WebP are smaller and optimized for web use. PNG are higher quality but larger in file size.

可用选项:

jpeg,

png,

webp

示例:

"webp"

height

integer

默认值:1024

Height of the generated image.

必填范围: 0 < x <= 1280

示例:

1024

hide_watermark

boolean

默认值:false

Whether to hide the Venice watermark. Venice may ignore this parameter for certain generated content.

示例:

false

inpaint

any | null

已弃用

This feature is deprecated and was disabled on May 19th, 2025. A revised in-painting API will be launched in the near future.

lora_strength

integer

Lora strength for the model. Only applies if the model uses additional Loras.

必填范围: 0 <= x <= 100

示例:

50

negative_prompt

string

A description of what should not be in the image. Character limit is model specific and is listed in the promptCharacterLimit constraint in the model list endpoint.

Maximum string length: 7500

示例:

"Clouds, Rain, Snow"

return_binary

boolean

默认值:false

Whether to return binary image data instead of base64.

示例:

false

variants

integer

Number of images to generate (1–4). Only supported when return_binary is false.

必填范围: 1 <= x <= 4

示例:

3

safe_mode

boolean

默认值:true

Whether to use safe mode. If enabled, this will blur images that are classified as having adult content.

示例:

false

seed

integer

默认值:0

Random seed for generation. If not provided, a random seed will be used.

必填范围: -999999999 <= x <= 999999999

示例:

123456789

steps

integer

默认值:8

Number of inference steps. This model does not support steps - this field is ignored.

示例:

8

style_preset

string

An image style to apply to the image. Visit https://docs.venice.ai/api-reference/endpoint/image/styles for more details.

示例:

"3D Model"

aspect_ratio

string

Aspect ratio (utilized by certain image models including Nano Banana). Examples: "1:1", "16:9".

示例:

"1:1"

resolution

string

Resolution (utilized by certain image models including Nano Banana). Examples: "1K", "2K", "4K".

示例:

"1K"

quality

enum<string>

Output quality for supported models (e.g. GPT Image 2 / GPT Image 2 Edit). Higher values can increase the final request charge. See the model list for supported options.

可用选项:

low,

medium,

high

示例:

"high"

enable_web_search

boolean

Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image. Only supported by certain models. If web search is used, additional credits are getting charged.

示例:

false

width

integer

默认值:1024

Width of the generated image.

必填范围: 0 < x <= 1280

示例:

1024

响应

Successfully generated image

string

必填

The ID of the request.

示例:

"generate-image-1234567890"

images

string[]

必填

Base64 encoded image data.

timing

object

必填

Show child attributes

request

any | null

The original request data sent to the API.

模型特性后缀放大和增强

⌘I

​尺寸选项

​质量等级

​Postman 集合

授权

请求头

请求体

响应

尺寸选项

质量等级

Postman 集合